{"id":2990,"url":"https://github.com/ICTMCG/Awesome-Machine-Generated-Text","name":"Awesome-Machine-Generated-Text","description":"Continuously updated list of related resources for generative LLMs like GPT and their analysis and detection.","projects_count":651,"last_synced_at":"2026-08-31T20:00:18.011Z","repository":{"id":109170640,"uuid":"596387185","full_name":"ICTMCG/Awesome-Machine-Generated-Text","owner":"ICTMCG","description":"Continuously updated list of related resources for generative LLMs like GPT and their analysis and detection.","archived":false,"fork":false,"pushed_at":"2025-05-28T03:12:17.000Z","size":661,"stargazers_count":231,"open_issues_count":1,"forks_count":16,"subscribers_count":11,"default_branch":"main","last_synced_at":"2026-08-12T05:08:10.659Z","etag":null,"topics":["ai-generated","awesome","chatgpt","detection","large-language-models","llm","machine-generated-text","paper-list"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ICTMCG.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2023-02-02T04:09:11.000Z","updated_at":"2026-07-08T12:31:07.000Z","dependencies_parsed_at":null,"dependency_job_id":"fc3958d6-5ac0-4078-af7b-1ef2792b157a","html_url":"https://github.com/ICTMCG/Awesome-Machine-Generated-Text","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ICTMCG/Awesome-Machine-Generated-Text","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ICTMCG%2FAwesome-Machine-Generated-Text","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ICTMCG%2FAwesome-Machine-Generated-Text/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ICTMCG%2FAwesome-Machine-Generated-Text/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ICTMCG%2FAwesome-Machine-Generated-Text/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ICTMCG","download_url":"https://codeload.github.com/ICTMCG/Awesome-Machine-Generated-Text/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ICTMCG%2FAwesome-Machine-Generated-Text/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":37007671,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-08-22T15:14:58.755Z","status":"online","status_checked_at":"2026-08-31T02:00:07.497Z","response_time":119,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"created_at":"2024-01-04T20:20:01.792Z","updated_at":"2026-08-31T20:00:18.011Z","primary_language":null,"list_of_lists":false,"displayable":true,"categories":["Large Scale Pre-training for Language Generation","Detection","TOC","Analysis"],"sub_categories":["Datasets","Comprehensive","Hallucination \u0026 Disinformation","Bias \u0026 Toxicity","Security Risk","LM Attack","Environment","Papers","Demos \u0026 Products","Shared Tasks"],"readme":"# Awesome Machine Generated Text\n\n## TOC\n- [Resource List about Machine Generated Text](#awesome-machine-generated-text)\n- [Awesome Machine Generated Text](#awesome-machine-generated-text)\n  - [TOC](#toc)\n  - [Large Scale Pre-training for Language Generation](#large-scale-pre-training-for-language-generation)\n  - [Analysis![](https://img.shields.io/badge/Building-red)](#analysis)\n    - [Comprehensive](#comprehensive)\n    - [Hallucination \\\u0026 Disinformation](#hallucination--disinformation)\n    - [Bias \\\u0026 Toxicity](#bias--toxicity)\n    - [Security Risk](#security-risk)\n    - [LM Attack](#lm-attack)\n    - [Environment](#environment)\n  - [Detection](#detection)\n    - [Papers](#papers)\n      - [Survey](#survey)\n      - [Human Detection](#human-detection)\n      - [Automatic Detection](#automatic-detection)\n      - [Detector Attack](#detector-attack)\n      - [Benchmark](#benchmark)\n      - [Watermarking](#watermarking)\n      - [Other Related Work](#other-related-work)\n    - [Demos \\\u0026 Products](#demos--products)\n    - [Datasets](#datasets)\n    - [Shared Tasks](#shared-tasks)\n\n## Large Scale Pre-training for Language Generation\n\u003e **Note:** #params \u003e 1B only\n\n- OpenAI\n  - (GPT-2) **Language Models are Unsupervised Multitask Learners.** [[paper]](https://cdn.openai.com/better-language-models/language_models_are_unsupervised_multitask_learners.pdf) [[blog]](https://openai.com/blog/better-language-models/) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/English-darkcyan) ![](https://img.shields.io/badge/Open-purple) ![](https://img.shields.io/badge/2019.02-blue)\n\n    *Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei and Ilya Sutskever.*\n\n  - (GPT-3) **Language Models are Few-Shot Learners.** [[paper]](https://proceedings.neurips.cc/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf) ![](https://img.shields.io/badge/NeurIPS%202020-orange) ![](https://img.shields.io/badge/Multilingual-darkcyan) ![](https://img.shields.io/badge/Limited-purple) ![](https://img.shields.io/badge/2020.05-blue)\n\n    \u003cdetails\u003e\u003csummary\u003eShow Authors\u003c/summary\u003e\u003ci\u003eTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever and Dario Amodei.\u003c/i\u003e\u003c/details\u003e\n\n  - **WebGPT: Browser-assisted question-answering with human feedback.** [[paper]](https://arxiv.org/pdf/2112.09332) [[blog]](https://openai.com/blog/webgpt/) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/Multilingual-darkcyan) ![](https://img.shields.io/badge/Closed-purple) ![](https://img.shields.io/badge/2021.12-blue)\n\n    *Reiichiro Nakano, Jacob Hilton, Suchir Balaji, Jeff Wu, Long Ouyang, Christina Kim, Christopher Hesse, Shantanu Jain, Vineet Kosaraju, William Saunders, Xu Jiang, Karl Cobbe, Tyna Eloundou, Gretchen Krueger, Kevin Button, Matthew Knight, Benjamin Chess and John Schulman.*\n\n  - (InstructGPT) **Training language models to follow instructions with human feedback.** [[paper]](https://arxiv.org/pdf/2203.02155) [[blog]](https://openai.com/blog/instruction-following/) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/Multilingual-darkcyan) ![](https://img.shields.io/badge/Limited-purple) ![](https://img.shields.io/badge/2022.01-blue)\n\n    *Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike and Ryan Lowe.*\n\n  - **ChatGPT: Optimizing Language Models for Dialogue.** [[blog]](https://openai.com/blog/chatgpt/) ![](https://img.shields.io/badge/Multilingual-darkcyan) ![](https://img.shields.io/badge/Limited-purple) ![](https://img.shields.io/badge/2022.11-blue)\n\n  - (GPT-4) **GPT-4 Technical Report.** [[paper]](https://cdn.openai.com/papers/gpt-4.pdf) [[blog]](https://openai.com/product/gpt-4) [[blog]](https://openai.com/research/gpt-4) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/Multilingual-darkcyan) ![](https://img.shields.io/badge/Limited-purple) ![](https://img.shields.io/badge/2023.03-blue)\n\n    *OpenAI.*\n\n- DeepMind\n  - (Gopher) **Scaling Language Models: Methods, Analysis \u0026 Insights from Training Gopher.** [[paper]](https://arxiv.org/pdf/2112.11446) [[blog]](https://www.deepmind.com/blog/language-modelling-at-scale-gopher-ethical-considerations-and-retrieval) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/English-darkcyan) ![](https://img.shields.io/badge/Closed-purple) ![](https://img.shields.io/badge/2021.12-blue)\n\n    \u003cdetails\u003e\u003csummary\u003eShow Authors\u003c/summary\u003e\u003ci\u003eJack W. Rae, Sebastian Borgeaud, Trevor Cai, Katie Millican, Jordan Hoffmann, Francis Song, John Aslanides, Sarah Henderson, Roman Ring, Susannah Young, Eliza Rutherford, Tom Hennigan, Jacob Menick, Albin Cassirer, Richard Powell, George van den Driessche, Lisa Anne Hendricks, Maribeth Rauh, Po-Sen Huang, Amelia Glaese, Johannes Welbl, Sumanth Dathathri, Saffron Huang, Jonathan Uesato, John Mellor, Irina Higgins, Antonia Creswell, Nat McAleese, Amy Wu, Erich Elsen, Siddhant Jayakumar, Elena Buchatskaya, David Budden, Esme Sutherland, Karen Simonyan, Michela Paganini, Laurent Sifre, Lena Martens, Xiang Lorraine Li, Adhiguna Kuncoro, Aida Nematzadeh, Elena Gribovskaya, Domenic Donato, Angeliki Lazaridou, Arthur Mensch, Jean-Baptiste Lespiau, Maria Tsimpoukelli, Nikolai Grigorev, Doug Fritz, Thibault Sottiaux, Mantas Pajarskas, Toby Pohlen, Zhitao Gong, Daniel Toyama, Cyprien de Masson d'Autume, Yujia Li, Tayfun Terzi, Vladimir Mikulik, Igor Babuschkin, Aidan Clark, Diego de Las Casas, Aurelia Guy, Chris Jones, James Bradbury, Matthew Johnson, Blake Hechtman, Laura Weidinger, Iason Gabriel, William Isaac, Ed Lockhart, Simon Osindero, Laura Rimell, Chris Dyer, Oriol Vinyals, Kareem Ayoub, Jeff Stanway, Lorrayne Bennett, Demis Hassabis, Koray Kavukcuoglu and Geoffrey Irving.\u003c/i\u003e\u003c/details\u003e\n\n  - (RETRO) **Improving language models by retrieving from trillions of tokens.** [[paper]](https://arxiv.org/pdf/2112.04426) [[blog]](https://www.deepmind.com/blog/improving-language-models-by-retrieving-from-trillions-of-tokens) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/English-darkcyan) ![](https://img.shields.io/badge/Closed-purple) ![](https://img.shields.io/badge/2021.12-blue)\n\n    \u003cdetails\u003e\u003csummary\u003eShow Authors\u003c/summary\u003e\u003ci\u003eSebastian Borgeaud, Arthur Mensch, Jordan Hoffmann, Trevor Cai, Eliza Rutherford, Katie Millican, George van den Driessche, Jean-Baptiste Lespiau, Bogdan Damoc, Aidan Clark, Diego de Las Casas, Aurelia Guy, Jacob Menick, Roman Ring, Tom Hennigan, Saffron Huang, Loren Maggiore, Chris Jones, Albin Cassirer, Andy Brock, Michela Paganini, Geoffrey Irving, Oriol Vinyals, Simon Osindero, Karen Simonyan, Jack W. Rae, Erich Elsen and Laurent Sifre.\u003c/i\u003e\u003c/details\u003e\n\n  - (Chinchilla) **Training Compute-Optimal Large Language Models.** [[paper]](https://arxiv.org/pdf/2203.15556) [[blog]](https://www.deepmind.com/blog/an-empirical-analysis-of-compute-optimal-large-language-model-training) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/English-darkcyan) ![](https://img.shields.io/badge/Closed-purple) ![](https://img.shields.io/badge/2022.04-blue)\n\n    \u003cdetails\u003e\u003csummary\u003eShow Authors\u003c/summary\u003e\u003ci\u003eJordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya, Trevor Cai, Eliza Rutherford, Diego de Las Casas, Lisa Anne Hendricks, Johannes Welbl, Aidan Clark, Tom Hennigan, Eric Noland, Katie Millican, George van den Driessche, Bogdan Damoc, Aurelia Guy, Simon Osindero, Karen Simonyan, Erich Elsen, Jack W. Rae, Oriol Vinyals and Laurent Sifre.\u003c/i\u003e\u003c/details\u003e\n  \n  - (Sparrow) **Improving alignment of dialogue agents via targeted human judgements.** [[paper]](https://arxiv.org/pdf/2209.14375) [[blog]](https://www.deepmind.com/blog/building-safer-dialogue-agents) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/English-darkcyan) ![](https://img.shields.io/badge/Closed-purple) ![](https://img.shields.io/badge/2022.09-blue)\n\n    \u003cdetails\u003e\u003csummary\u003eShow Authors\u003c/summary\u003e\u003ci\u003eAmelia Glaese, Nat McAleese, Maja Trębacz, John Aslanides, Vlad Firoiu, Timo Ewalds, Maribeth Rauh, Laura Weidinger, Martin Chadwick, Phoebe Thacker, Lucy Campbell-Gillingham, Jonathan Uesato, Po-Sen Huang, Ramona Comanescu, Fan Yang, Abigail See, Sumanth Dathathri, Rory Greig, Charlie Chen, Doug Fritz, Jaume Sanchez Elias, Richard Green, Soňa Mokrá, Nicholas Fernando, Boxi Wu, Rachel Foley, Susannah Young, Iason Gabriel, William Isaac, John Mellor, Demis Hassabis, Koray Kavukcuoglu, Lisa Anne Hendricks and Geoffrey Irving.\u003c/i\u003e\u003c/details\u003e\n\n- Nvidia \u0026 Microsoft\n  - **Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism.** [[paper]](https://arxiv.org/pdf/1909.08053) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/English-darkcyan) ![](https://img.shields.io/badge/Limited-purple) ![](https://img.shields.io/badge/2019.09-blue)\n\n    *Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper and Bryan Catanzaro.*\n\n  - **Turing-NLG: A 17-billion-parameter language model by Microsoft.** [[blog]](https://www.microsoft.com/en-us/research/blog/turing-nlg-a-17-billion-parameter-language-model-by-microsoft/) ![](https://img.shields.io/badge/English-darkcyan) ![](https://img.shields.io/badge/Closed-purple) ![](https://img.shields.io/badge/2020.02-blue)\n\n  - (Megatron-Turing NLG) **Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model.** [[paper]](https://arxiv.org/pdf/2201.11990) [[blog]](https://developer.nvidia.com/blog/using-deepspeed-and-megatron-to-train-megatron-turing-nlg-530b-the-worlds-largest-and-most-powerful-generative-language-model/) [[blog]](https://www.microsoft.com/en-us/research/blog/using-deepspeed-and-megatron-to-train-megatron-turing-nlg-530b-the-worlds-largest-and-most-powerful-generative-language-model/) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/English-darkcyan) ![](https://img.shields.io/badge/Closed-purple) ![](https://img.shields.io/badge/2021.10-blue)\n\n    \u003cdetails\u003e\u003csummary\u003eShow Authors\u003c/summary\u003e\u003ci\u003eShaden Smith, Mostofa Patwary, Brandon Norick, Patrick LeGresley, Samyam Rajbhandari, Jared Casper, Zhun Liu, Shrimai Prabhumoye, George Zerveas, Vijay Korthikanti, Elton Zhang, Rewon Child, Reza Yazdani Aminabadi, Julie Bernauer, Xia Song, Mohammad Shoeybi, Yuxiong He, Michael Houston, Saurabh Tiwary and Bryan Catanzaro.\u003c/i\u003e\u003c/details\u003e\n\n- Google\n  - (Meena) **Towards a Human-like Open-Domain Chatbot.** [[paper]](https://arxiv.org/pdf/2001.09977) [[blog]](https://ai.googleblog.com/2020/01/towards-conversational-agent-that-can.html) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/English-darkcyan) ![](https://img.shields.io/badge/Closed-purple) ![](https://img.shields.io/badge/2020.01-blue)\n\n    *Daniel Adiwardana, Minh-Thang Luong, David R. So, Jamie Hall, Noah Fiedel, Romal Thoppilan, Zi Yang, Apoorv Kulshreshtha, Gaurav Nemade, Yifeng Lu and Quoc V. Le.*\n\n  - (T5) **Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer.** [[paper]](https://www.jmlr.org/papers/volume21/20-074/20-074.pdf) [[blog]](https://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html) ![](https://img.shields.io/badge/JMLR%202020-orange) ![](https://img.shields.io/badge/English-darkcyan) ![](https://img.shields.io/badge/Open-purple) ![](https://img.shields.io/badge/2020.02-blue)\n\n    *Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li and Peter J. Liu.*\n\n  - **mT5: A massively multilingual pre-trained text-to-text transformer.** [[paper]](https://aclanthology.org/2021.naacl-main.41.pdf) ![](https://img.shields.io/badge/NAACL%202021-orange) ![](https://img.shields.io/badge/Multilingual-darkcyan) ![](https://img.shields.io/badge/Open-purple) ![](https://img.shields.io/badge/2020.10-blue)\n\n    *Linting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua and Colin Raffel.*\n\n  - (FLAN) **Finetuned Language Models Are Zero-Shot Learners.** [[paper]](https://openreview.net/pdf?id=gEZrGCozdqR) [[blog]](https://ai.googleblog.com/2021/10/introducing-flan-more-generalizable.html) ![](https://img.shields.io/badge/ICLR%202022-orange) ![](https://img.shields.io/badge/English-darkcyan) ![](https://img.shields.io/badge/Closed-purple) ![](https://img.shields.io/badge/2021.10-blue)\n\n    *Jason Wei, Maarten Bosma, Vincent Y. Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M. Dai and Quoc V. Le.*\n\n  - **GLaM: Efficient Scaling of Language Models with Mixture-of-Experts.** [[paper]](https://arxiv.org/pdf/2112.06905) [[slides]](https://icml.cc/media/icml-2022/Slides/17378.pdf) [[blog]](https://ai.googleblog.com/2021/12/more-efficient-in-context-learning-with.html) ![](https://img.shields.io/badge/ICML%202022-orange) ![](https://img.shields.io/badge/English-darkcyan) ![](https://img.shields.io/badge/Closed-purple) ![](https://img.shields.io/badge/2021.12-blue)\n\n    \u003cdetails\u003e\u003csummary\u003eShow Authors\u003c/summary\u003e\u003ci\u003eNan Du, Yanping Huang, Andrew M. Dai, Simon Tong, Dmitry Lepikhin, Yuanzhong Xu, Maxim Krikun, Yanqi Zhou, Adams Wei Yu, Orhan Firat, Barret Zoph, Liam Fedus, Maarten Bosma, Zongwei Zhou, Tao Wang, Yu Emma Wang, Kellie Webster, Marie Pellat, Kevin Robinson, Kathleen Meier-Hellstern, Toju Duke, Lucas Dixon, Kun Zhang, Quoc V Le, Yonghui Wu, Zhifeng Chen and Claire Cui.\u003c/i\u003e\u003c/details\u003e\n  \n  - **LaMDA: Language Models for Dialog Applications.** [[paper]](https://arxiv.org/pdf/2201.08239) [[blog]](https://ai.googleblog.com/2022/01/lamda-towards-safe-grounded-and-high.html) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/English-darkcyan) ![](https://img.shields.io/badge/Closed-purple) ![](https://img.shields.io/badge/2022.01-blue)\n\n    \u003cdetails\u003e\u003csummary\u003eShow Authors\u003c/summary\u003e\u003ci\u003eRomal Thoppilan, Daniel De Freitas, Jamie Hall, Noam Shazeer, Apoorv Kulshreshtha, Heng-Tze Cheng, Alicia Jin, Taylor Bos, Leslie Baker, Yu Du, YaGuang Li, Hongrae Lee, Huaixiu Steven Zheng, Amin Ghafouri, Marcelo Menegali, Yanping Huang, Maxim Krikun, Dmitry Lepikhin, James Qin, Dehao Chen, Yuanzhong Xu, Zhifeng Chen, Adam Roberts, Maarten Bosma, Vincent Zhao, Yanqi Zhou, Chung-Ching Chang, Igor Krivokon, Will Rusch, Marc Pickett, Pranesh Srinivasan, Laichee Man, Kathleen Meier-Hellstern, Meredith Ringel Morris, Tulsee Doshi, Renelito Delos Santos, Toju Duke, Johnny Soraker, Ben Zevenbergen, Vinodkumar Prabhakaran, Mark Diaz, Ben Hutchinson, Kristen Olson, Alejandra Molina, Erin Hoffman-John, Josh Lee, Lora Aroyo, Ravi Rajakumar, Alena Butryna, Matthew Lamm, Viktoriya Kuzmina, Joe Fenton, Aaron Cohen, Rachel Bernstein, Ray Kurzweil, Blaise Aguera-Arcas, Claire Cui, Marian Croak, Ed Chi and Quoc Le.\u003c/i\u003e\u003c/details\u003e\n\n  - **PaLM: Scaling Language Modeling with Pathways.** [[paper]](https://arxiv.org/pdf/2204.02311) [[blog]](https://ai.googleblog.com/2022/04/pathways-language-model-palm-scaling-to.html) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/English-darkcyan) ![](https://img.shields.io/badge/Closed-purple) ![](https://img.shields.io/badge/2022.04-blue)\n\n    \u003cdetails\u003e\u003csummary\u003eShow Authors\u003c/summary\u003e\u003ci\u003eAakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, Parker Schuh, Kensen Shi, Sasha Tsvyashchenko, Joshua Maynez, Abhishek Rao, Parker Barnes, Yi Tay, Noam Shazeer, Vinodkumar Prabhakaran, Emily Reif, Nan Du, Ben Hutchinson, Reiner Pope, James Bradbury, Jacob Austin, Michael Isard, Guy Gur-Ari, Pengcheng Yin, Toju Duke, Anselm Levskaya, Sanjay Ghemawat, Sunipa Dev, Henryk Michalewski, Xavier Garcia, Vedant Misra, Kevin Robinson, Liam Fedus, Denny Zhou, Daphne Ippolito, David Luan, Hyeontaek Lim, Barret Zoph, Alexander Spiridonov, Ryan Sepassi, David Dohan, Shivani Agrawal, Mark Omernick, Andrew M. Dai, Thanumalayan Sankaranarayana Pillai, Marie Pellat, Aitor Lewkowycz, Erica Moreira, Rewon Child, Oleksandr Polozov, Katherine Lee, Zongwei Zhou, Xuezhi Wang, Brennan Saeta, Mark Diaz, Orhan Firat, Michele Catasta, Jason Wei, Kathy Meier-Hellstern, Douglas Eck, Jeff Dean, Slav Petrov and Noah Fiedel.\u003c/i\u003e\u003c/details\u003e\n\n  - **UL2: Unifying Language Learning Paradigms.** [[paper]](https://arxiv.org/pdf/2205.05131) [[blog]](https://ai.googleblog.com/2022/10/ul2-20b-open-source-unified-language.html) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/English-darkcyan) ![](https://img.shields.io/badge/Open-purple) ![](https://img.shields.io/badge/2022.10-blue)\n\n    *Yi Tay, Mostafa Dehghani, Vinh Q. Tran, Xavier Garcia, Jason Wei, Xuezhi Wang, Hyung Won Chung, Dara Bahri, Tal Schuster, Huaixiu Steven Zheng, Denny Zhou, Neil Houlsby and Donald Metzler.*\n  \n  - (Flan-T5 \u0026 Flan-PaLM \u0026 Flan-U-PaLM) **Scaling Instruction-Finetuned Language Models.** [[paper]](https://arxiv.org/pdf/2210.11416) [[blog]](https://ai.googleblog.com/2022/10/ul2-20b-open-source-unified-language.html) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/English-darkcyan) ![](https://img.shields.io/badge/Open-purple) ![](https://img.shields.io/badge/2022.10-blue)\n\n    *Yi Tay, Mostafa Dehghani, Vinh Q. Tran, Xavier Garcia, Jason Wei, Xuezhi Wang, Hyung Won Chung, Dara Bahri, Tal Schuster, Huaixiu Steven Zheng, Denny Zhou, Neil Houlsby and Donald Metzler.*\n\n- Meta\n  - (Generative BST) **Recipes for Building an Open-Domain Chatbot.** [[paper]](https://aclanthology.org/2021.eacl-main.24.pdf) ![](https://img.shields.io/badge/EACL%202021-orange) ![](https://img.shields.io/badge/English-darkcyan) ![](https://img.shields.io/badge/Open-purple) ![](https://img.shields.io/badge/2020.04-blue)\n\n    *Stephen Roller, Emily Dinan, Naman Goyal, Da Ju, Mary Williamson, Yinhan Liu, Jing Xu, Myle Ott, Kurt Shuster, Eric M. Smith, Y-Lan Boureau and Jason Weston.*\n  \n  - (XGLM) **Few-shot Learning with Multilingual Language Models.** [[paper]](https://arxiv.org/pdf/2112.10668) ![](https://img.shields.io/badge/EMNLP%202022-orange) ![](https://img.shields.io/badge/Multilingual-darkcyan) ![](https://img.shields.io/badge/Open-purple) ![](https://img.shields.io/badge/2021.12-blue)\n\n    *Xi Victoria Lin, Todor Mihaylov, Mikel Artetxe, Tianlu Wang, Shuohui Chen, Daniel Simig, Myle Ott, Naman Goyal, Shruti Bhosale, Jingfei Du, Ramakanth Pasunuru, Sam Shleifer, Punit Singh Koura, Vishrav Chaudhary, Brian O'Horo, Jeff Wang, Luke Zettlemoyer, Zornitsa Kozareva, Mona Diab, Veselin Stoyanov and Xian Li.*\n  \n  - **OPT: Open Pre-trained Transformer Language Models.** [[paper]](https://arxiv.org/pdf/2205.01068) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/English-darkcyan) ![](https://img.shields.io/badge/Open-purple) ![](https://img.shields.io/badge/2022.05-blue)\n\n    *Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang and Luke Zettlemoyer.*\n  \n  - **BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage.** [[paper]](https://arxiv.org/pdf/2208.03188) [[blog]](https://ai.facebook.com/blog/blenderbot-3-a-175b-parameter-publicly-available-chatbot-that-improves-its-skills-and-safety-over-time/) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/English-darkcyan) ![](https://img.shields.io/badge/Closed-purple) ![](https://img.shields.io/badge/2022.08-blue)\n\n    *Kurt Shuster, Jing Xu, Mojtaba Komeili, Da Ju, Eric Michael Smith, Stephen Roller, Megan Ung, Moya Chen, Kushal Arora, Joshua Lane, Morteza Behrooz, William Ngan, Spencer Poff, Naman Goyal, Arthur Szlam, Y-Lan Boureau, Melanie Kambadur and Jason Weston.*\n  \n  - **Atlas: Few-shot Learning with Retrieval Augmented Language Models.** [[paper]](https://arxiv.org/pdf/2208.03299) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/English-darkcyan) ![](https://img.shields.io/badge/Open-purple) ![](https://img.shields.io/badge/2022.08-blue)\n\n    *Gautier Izacard, Patrick Lewis, Maria Lomeli, Lucas Hosseini, Fabio Petroni, Timo Schick, Jane Dwivedi-Yu, Armand Joulin, Sebastian Riedel and Edouard Grave.*\n\n  - **LLaMA: Open and Efficient Foundation Language Models.** [[paper]](https://research.facebook.com/file/1574548786327032/LLaMA--Open-and-Efficient-Foundation-Language-Models.pdf) [[blog]](https://ai.facebook.com/blog/large-language-model-llama-meta-ai/) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/Multilingual-darkcyan) ![](https://img.shields.io/badge/Open-purple) ![](https://img.shields.io/badge/2023.02-blue)\n\n    *Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave and Guillaume Lample.*\n\n- BigScience\n  - (T0++) **Multitask Prompted Training Enables Zero-Shot Task Generalization.** [[paper]](https://openreview.net/pdf?id=9Vrb9D0WI4) ![](https://img.shields.io/badge/ICLR%202022-orange) ![](https://img.shields.io/badge/English-darkcyan) ![](https://img.shields.io/badge/Open-purple) ![](https://img.shields.io/badge/2021.10-blue)\n\n    \u003cdetails\u003e\u003csummary\u003eShow Authors\u003c/summary\u003e\u003ci\u003eVictor Sanh, Albert Webson, Colin Raffel, Stephen H. Bach, Lintang Sutawika, Zaid Alyafeai, Antoine Chaffin, Arnaud Stiegler, Teven Le Scao, Arun Raja, Manan Dey, M Saiful Bari, Canwen Xu, Urmish Thakker, Shanya Sharma Sharma, Eliza Szczechla, Taewoon Kim, Gunjan Chhablani, Nihal Nayak, Debajyoti Datta, Jonathan Chang, Mike Tian-Jian Jiang, Han Wang, Matteo Manica, Sheng Shen, Zheng Xin Yong, Harshit Pandey, Rachel Bawden, Thomas Wang, Trishala Neeraj, Jos Rozen, Abheesht Sharma, Andrea Santilli, Thibault Fevry, Jason Alan Fries, Ryan Teehan, Tali Bers, Stella Biderman, Leo Gao, Thomas Wolf and Alexander M. Rush.\u003c/i\u003e\u003c/details\u003e\n  \n  - **BLOOM: A 176B-Parameter Open-Access Multilingual Language Model.** [[paper]](https://arxiv.org/pdf/2211.05100) ![](https://img.shields.io/badge/Preprint-orange)  ![](https://img.shields.io/badge/Multilingual-darkcyan) ![](https://img.shields.io/badge/Open-purple) ![](https://img.shields.io/badge/2022.11-blue)\n\n    \u003cdetails\u003e\u003csummary\u003eShow Authors\u003c/summary\u003e\u003ci\u003eBigScience Workshop: Teven Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ilić, Daniel Hesslow, Roman Castagné, Alexandra Sasha Luccioni, François Yvon, Matthias Gallé, Jonathan Tow, Alexander M. Rush, Stella Biderman, Albert Webson, Pawan Sasanka Ammanamanchi, Thomas Wang, Benoît Sagot, Niklas Muennighoff, Albert Villanova del Moral, Olatunji Ruwase, Rachel Bawden, Stas Bekman, Angelina McMillan-Major, Iz Beltagy, Huu Nguyen, Lucile Saulnier, Samson Tan, Pedro Ortiz Suarez, Victor Sanh, Hugo Laurençon, Yacine Jernite, Julien Launay, Margaret Mitchell, Colin Raffel, Aaron Gokaslan, Adi Simhi, Aitor Soroa, Alham Fikri Aji, Amit Alfassy, Anna Rogers, Ariel Kreisberg Nitzav, Canwen Xu, Chenghao Mou, Chris Emezue, Christopher Klamm, Colin Leong, Daniel van Strien, David Ifeoluwa Adelani, Dragomir Radev, Eduardo González Ponferrada, Efrat Levkovizh, Ethan Kim, Eyal Bar Natan, Francesco De Toni, Gérard Dupont, Germán Kruszewski, Giada Pistilli, Hady Elsahar, Hamza Benyamina, Hieu Tran, Ian Yu, Idris Abdulmumin, Isaac Johnson, Itziar Gonzalez-Dios, Javier de la Rosa, Jenny Chim, Jesse Dodge, Jian Zhu, Jonathan Chang, Jörg Frohberg, Joseph Tobing, Joydeep Bhattacharjee, Khalid Almubarak, Kimbo Chen, Kyle Lo, Leandro Von Werra, Leon Weber, Long Phan, Loubna Ben allal, Ludovic Tanguy, Manan Dey, Manuel Romero Muñoz, Maraim Masoud, María Grandury, Mario Šaško, Max Huang, Maximin Coavoux, Mayank Singh, Mike Tian-Jian Jiang, Minh Chien Vu, Mohammad A. Jauhar, Mustafa Ghaleb, Nishant Subramani, Nora Kassner, Nurulaqilla Khamis, Olivier Nguyen, Omar Espejel, Ona de Gibert, Paulo Villegas , Peter Henderson, Pierre Colombo, Priscilla Amuok, Quentin Lhoest, Rheza Harliman, Rishi Bommasani, Roberto Luis López, Rui Ribeiro, Salomey Osei, Sampo Pyysalo, Sebastian Nagel, Shamik Bose, Shamsuddeen Hassan Muhammad, Shanya Sharma, Shayne Longpre, Somaieh Nikpoor, Stanislav Silberberg, Suhas Pai, Sydney Zink, Tiago Timponi Torrent, Timo Schick, Tristan Thrush, Valentin Danchev, Vassilina Nikoulina, Veronika Laippala, Violette Lepercq, Vrinda Prabhu, Zaid Alyafeai, Zeerak Talat, Arun Raja, Benjamin Heinzerling, Chenglei Si, Davut Emre Taşar, Elizabeth Salesky, Sabrina J. Mielke, Wilson Y. Lee, Abheesht Sharma, Andrea Santilli, Antoine Chaffin, Arnaud Stiegler, Debajyoti Datta, Eliza Szczechla, Gunjan Chhablani, Han Wang, Harshit Pandey, Hendrik Strobelt, Jason Alan Fries, Jos Rozen, Leo Gao, Lintang Sutawika, M Saiful Bari, Maged S. Al-shaibani, Matteo Manica, Nihal Nayak, Ryan Teehan, Samuel Albanie, Sheng Shen, Srulik Ben-David, Stephen H. Bach, Taewoon Kim, Tali Bers, Thibault Fevry, Trishala Neeraj, Urmish Thakker, Vikas Raunak, Xiangru Tang, Zheng-Xin Yong, Zhiqing Sun, Shaked Brody, Yallow Uri, Hadar Tojarieh, Adam Roberts, Hyung Won Chung, Jaesung Tae, Jason Phang, Ofir Press, Conglong Li, Deepak Narayanan, Hatim Bourfoune, Jared Casper, Jeff Rasley, Max Ryabinin, Mayank Mishra, Minjia Zhang, Mohammad Shoeybi, Myriam Peyrounette, Nicolas Patry, Nouamane Tazi, Omar Sanseviero, Patrick von Platen, Pierre Cornette, Pierre François Lavallée, Rémi Lacroix, Samyam Rajbhandari, Sanchit Gandhi, Shaden Smith, Stéphane Requena, Suraj Patil, Tim Dettmers, Ahmed Baruwa, Amanpreet Singh, Anastasia Cheveleva, Anne-Laure Ligozat, Arjun Subramonian, Aurélie Névéol, Charles Lovering, Dan Garrette, Deepak Tunuguntla, Ehud Reiter, Ekaterina Taktasheva, Ekaterina Voloshina, Eli Bogdanov, Genta Indra Winata, Hailey Schoelkopf, Jan-Christoph Kalo, Jekaterina Novikova, Jessica Zosa Forde, Jordan Clive, Jungo Kasai, Ken Kawamura, Liam Hazan, Marine Carpuat, Miruna Clinciu, Najoung Kim, Newton Cheng, Oleg Serikov, Omer Antverg, Oskar van der Wal, Rui Zhang, Ruochen Zhang, Sebastian Gehrmann, Shachar Mirkin, Shani Pais, Tatiana Shavrina, Thomas Scialom, Tian Yun, Tomasz Limisiewicz, Verena Rieser, Vitaly Protasov, Vladislav Mikhailov, Yada Pruksachatkun, Yonatan Belinkov, Zachary Bamberger, Zdeněk Kasner, Alice Rueda, Amanda Pestana, Amir Feizpour, Ammar Khan, Amy Faranak, Ana Santos, Anthony Hevia, Antigona Unldreaj, Arash Aghagol, Arezoo Abdollahi, Aycha Tammour, Azadeh HajiHosseini, Bahareh Behroozi, Benjamin Ajibade, Bharat Saxena, Carlos Muñoz Ferrandis, Danish Contractor, David Lansky, Davis David, Douwe Kiela, Duong A. Nguyen, Edward Tan, Emi Baylor, Ezinwanne Ozoani, Fatima Mirza, Frankline Ononiwu, Habib Rezanejad, Hessie Jones, Indrani Bhattacharya, Irene Solaiman, Irina Sedenko, Isar Nejadgholi, Jesse Passmore, Josh Seltzer, Julio Bonis Sanz, Livia Dutra, Mairon Samagaio, Maraim Elbadri, Margot Mieskes, Marissa Gerchick, Martha Akinlolu, Michael McKenna, Mike Qiu, Muhammed Ghauri, Mykola Burynok, Nafis Abrar, Nazneen Rajani, Nour Elkott, Nour Fahmy, Olanrewaju Samuel, Ran An, Rasmus Kromann, Ryan Hao, Samira Alizadeh, Sarmad Shubber, Silas Wang, Sourav Roy, Sylvain Viguier, Thanh Le, Tobi Oyebade, Trieu Le, Yoyo Yang, Zach Nguyen, Abhinav Ramesh Kashyap, Alfredo Palasciano, Alison Callahan, Anima Shukla, Antonio Miranda-Escalada, Ayush Singh, Benjamin Beilharz, Bo Wang, Caio Brito, Chenxi Zhou, Chirag Jain, Chuxin Xu, Clémentine Fourrier, Daniel León Periñán, Daniel Molano, Dian Yu, Enrique Manjavacas, Fabio Barth, Florian Fuhrimann, Gabriel Altay, Giyaseddin Bayrak, Gully Burns, Helena U. Vrabec, Imane Bello, Ishani Dash, Jihyun Kang, John Giorgi, Jonas Golde, Jose David Posada, Karthik Rangasai Sivaraman, Lokesh Bulchandani, Lu Liu, Luisa Shinzato, Madeleine Hahn de Bykhovetz, Maiko Takeuchi, Marc Pàmies, Maria A Castillo, Marianna Nezhurina, Mario Sänger, Matthias Samwald, Michael Cullan, Michael Weinberg, Michiel De Wolf, Mina Mihaljcic, Minna Liu, Moritz Freidank, Myungsun Kang, Natasha Seelam, Nathan Dahlberg, Nicholas Michio Broad, Nikolaus Muellner, Pascale Fung, Patrick Haller, Ramya Chandrasekhar, Renata Eisenberg, Robert Martin, Rodrigo Canalli, Rosaline Su, Ruisi Su, Samuel Cahyawijaya, Samuele Garda, Shlok S Deshmukh, Shubhanshu Mishra, Sid Kiblawi, Simon Ott, Sinee Sang-aroonsiri, Srishti Kumar, Stefan Schweter, Sushil Bharati, Tanmay Laud, Théo Gigant, Tomoya Kainuma, Wojciech Kusa, Yanis Labrak, Yash Shailesh Bajaj, Yash Venkatraman, Yifan Xu, Yingxin Xu, Yu Xu, Zhe Tan, Zhongli Xie, Zifan Ye, Mathilde Bras, Younes Belkada and Thomas Wolf.\u003c/i\u003e\u003c/details\u003e\n\n- Amazon\n  - **AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model.** [[paper]](https://arxiv.org/pdf/2208.01448) [[blog]](https://www.amazon.science/blog/20b-parameter-alexa-model-sets-new-marks-in-few-shot-learning) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/English-darkcyan) ![](https://img.shields.io/badge/Limited-purple) ![](https://img.shields.io/badge/2022.08-blue)\n\n    *Saleh Soltan, Shankar Ananthakrishnan, Jack FitzGerald, Rahul Gupta, Wael Hamza, Haidar Khan, Charith Peris, Stephen Rawls, Andy Rosenbaum, Anna Rumshisky, Chandana Satya Prakash, Mukund Sridhar, Fabian Triefenbach, Apurv Verma, Gokhan Tur and Prem Natarajan.*\n\n- AI21 Labs\n  - **Jurassic-1: Technical Details and Evaluation.** [[paper]](https://uploads-ssl.webflow.com/60fd4503684b466578c0d307/61138924626a6981ee09caf6_jurassic_tech_paper.pdf) [[blog]](https://www.ai21.com/blog/announcing-ai21-studio-and-jurassic-1) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/English-darkcyan) ![](https://img.shields.io/badge/Limited-purple) ![](https://img.shields.io/badge/2021.08-blue)\n\n    *Opher Lieber, Or Sharir, Barak Lenz and Yoav Shoham.*\n\n- Baidu\n  - **ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation.** [[paper]](https://arxiv.org/pdf/2107.02137) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/Multilingual-darkcyan) ![](https://img.shields.io/badge/Limited-purple) ![](https://img.shields.io/badge/2021.07-blue)\n\n    *Yu Sun, Shuohuan Wang, Shikun Feng, Siyu Ding, Chao Pang, Junyuan Shang, Jiaxiang Liu, Xuyi Chen, Yanbin Zhao, Yuxiang Lu, Weixin Liu, Zhihua Wu, Weibao Gong, Jianzhong Liang, Zhizhou Shang, Peng Sun, Wei Liu, Xuan Ouyang, Dianhai Yu, Hao Tian, Hua Wu and Haifeng Wang.*\n\n  - **ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation.** [[paper]](https://arxiv.org/pdf/2112.12731) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/Multilingual-darkcyan) ![](https://img.shields.io/badge/Closed-purple) ![](https://img.shields.io/badge/2021.12-blue)\n\n    \u003cdetails\u003e\u003csummary\u003eShow Authors\u003c/summary\u003e\u003ci\u003eShuohuan Wang, Yu Sun, Yang Xiang, Zhihua Wu, Siyu Ding, Weibao Gong, Shikun Feng, Junyuan Shang, Yanbin Zhao, Chao Pang, Jiaxiang Liu, Xuyi Chen, Yuxiang Lu, Weixin Liu, Xi Wang, Yangfan Bai, Qiuliang Chen, Li Zhao, Shiyong Li, Peng Sun, Dianhai Yu, Yanjun Ma, Hao Tian, Hua Wu, Tian Wu, Wei Zeng, Ge Li, Wen Gao and Haifeng Wang.\u003c/i\u003e\u003c/details\u003e\n\n  - **PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generation.** [[paper]](https://aclanthology.org/2022.findings-aacl.10.pdf) ![](https://img.shields.io/badge/AACL--IJCNLP%202022%20Findings-orange) ![](https://img.shields.io/badge/Multilingual-darkcyan) ![](https://img.shields.io/badge/Open-purple) ![](https://img.shields.io/badge/2021.09-blue)\n\n    *Siqi Bao, Huang He, Fan Wang, Hua Wu, Haifeng Wang, Wenquan Wu, Zhihua Wu, Zhen Guo, Hua Lu, Xinxian Huang, Xin Tian, Xinchao Xu, Yingzhan Lin and Zheng-Yu Niu.*\n\n  - ERNIE Bot [[news]](https://mp.weixin.qq.com/s/0-8X9FPouteKzNiK6DPaiA) ![](https://img.shields.io/badge/2023.02-blue)\n\n- Anthropic\n  - (Anthropic-52) **Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback** [[paper]](https://arxiv.org/pdf/2204.05862) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/English-darkcyan) ![](https://img.shields.io/badge/Closed-purple) ![](https://img.shields.io/badge/2022.04-blue)\n\n    \u003cdetails\u003e\u003csummary\u003eShow Authors\u003c/summary\u003e\u003ci\u003eYuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, Nicholas Joseph, Saurav Kadavath, Jackson Kernion, Tom Conerly, Sheer El-Showk, Nelson Elhage, Zac Hatfield-Dodds, Danny Hernandez, Tristan Hume, Scott Johnston, Shauna Kravec, Liane Lovitt, Neel Nanda, Catherine Olsson, Dario Amodei, Tom Brown, Jack Clark, Sam McCandlish, Chris Olah, Ben Mann and Jared Kaplan.\u003c/i\u003e\u003c/details\u003e\n\n  - (Claude) **Constitutional AI: Harmlessness from AI Feedback.** [[paper]](https://arxiv.org/pdf/2212.08073) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/English-darkcyan) ![](https://img.shields.io/badge/Closed-purple) ![](https://img.shields.io/badge/2022.12-blue)\n\n    \u003cdetails\u003e\u003csummary\u003eShow Authors\u003c/summary\u003e\u003ci\u003eYuntao Bai, Saurav Kadavath, Sandipan Kundu, Amanda Askell, Jackson Kernion, Andy Jones, Anna Chen, Anna Goldie, Azalia Mirhoseini, Cameron McKinnon, Carol Chen, Catherine Olsson, Christopher Olah, Danny Hernandez, Dawn Drain, Deep Ganguli, Dustin Li, Eli Tran-Johnson, Ethan Perez, Jamie Kerr, Jared Mueller, Jeffrey Ladish, Joshua Landau, Kamal Ndousse, Kamile Lukosuite, Liane Lovitt, Michael Sellitto, Nelson Elhage, Nicholas Schiefer, Noemi Mercado, Nova DasSarma, Robert Lasenby, Robin Larson, Sam Ringer, Scott Johnston, Shauna Kravec, Sheer El Showk, Stanislav Fort, Tamera Lanham, Timothy Telleen-Lawton, Tom Conerly, Tom Henighan, Tristan Hume, Samuel R. Bowman, Zac Hatfield-Dodds, Ben Mann, Dario Amodei, Nicholas Joseph, Sam McCandlish, Tom Brown and Jared Kaplan.\u003c/i\u003e\u003c/details\u003e\n\n- EleutherAI\n  - **GPT-J-6B: 6B JAX-Based Transformer.** [[blog]](https://arankomatsuzaki.wordpress.com/2021/06/04/gpt-j/) ![](https://img.shields.io/badge/English-darkcyan) ![](https://img.shields.io/badge/Open-purple) ![](https://img.shields.io/badge/2021.06-blue)\n\n  - **GPT-NeoX-20B: An Open-Source Autoregressive Language Model.** [[paper]](https://aclanthology.org/2022.bigscience-1.9.pdf) [[blog]](https://blog.eleuther.ai/announcing-20b/) ![](https://img.shields.io/badge/ACL%202022%20Workshop-orange) ![](https://img.shields.io/badge/English-darkcyan) ![](https://img.shields.io/badge/Open-purple) ![](https://img.shields.io/badge/2022.02-blue)\n\n    *Sid Black, Stella Biderman, Eric Hallahan, Quentin Anthony, Leo Gao, Laurence Golding, Horace He, Connor Leahy, Kyle McDonell, Jason Phang, Michael Pieler, USVSN Sai Prashanth, Shivanshu Purohit, Laria Reynolds, Jonathan Tow, Ben Wang, Samuel Weinbach.*\n\n- Tsinghua University\n  - **CPM: A Large-scale Generative Chinese Pre-trained Language Model.** [[paper]](https://www.sciencedirect.com/science/article/pii/S266665102100019X/pdfft?md5=c9c82038f6f237b8708270ed0fbbf80b\u0026pid=1-s2.0-S266665102100019X-main.pdf) ![](https://img.shields.io/badge/AI%20Open%202021-orange) ![](https://img.shields.io/badge/Chinese-darkcyan) ![](https://img.shields.io/badge/Open-purple) ![](https://img.shields.io/badge/2020.12-blue)\n\n    *Zhengyan Zhang, Xu Han, Hao Zhou, Pei Ke, Yuxian Gu, Deming Ye, Yujia Qin, Yusheng Su, Haozhe Ji, Jian Guan, Fanchao Qi, Xiaozhi Wang, Yanan Zheng, Guoyang Zeng, Huanqi Cao, Shengqi Chen, Daixuan Li, Zhenbo Sun, Zhiyuan Liu, Minlie Huang, Wentao Han, Jie Tang, Juanzi Li, Xiaoyan Zhu, Maosong Sun.*\n  \n  - **CPM-2: Large-scale Cost-effective Pre-trained Language Models.** [[paper]](https://www.sciencedirect.com/science/article/pii/S2666651021000310/pdfft?md5=46efc536c128aefd0ff69139f8627ddb\u0026pid=1-s2.0-S2666651021000310-main.pdf) ![](https://img.shields.io/badge/AI%20Open%202021-orange) ![](https://img.shields.io/badge/Multilingual-darkcyan) ![](https://img.shields.io/badge/Open-purple) ![](https://img.shields.io/badge/2021.06-blue)\n\n    *Zhengyan Zhang, Yuxian Gu, Xu Han, Shengqi Chen, Chaojun Xiao, Zhenbo Sun, Yuan Yao, Fanchao Qi, Jian Guan, Pei Ke, Yanzheng Cai, Guoyang Zeng, Zhixing Tan, Zhiyuan Liu, Minlie Huang, Wentao Han, Yang Liu, Xiaoyan Zhu, Maosong Sun.*\n\n  - Chinese-Transformer-XL [[repo]](https://github.com/THUDM/Chinese-Transformer-XL) ![](https://img.shields.io/badge/Chinese-darkcyan) ![](https://img.shields.io/badge/Open-purple) ![](https://img.shields.io/badge/2021.03-blue)\n  \n  - **EVA: An Open-Domain Chinese Dialogue System with Large-Scale Generative Pre-Training.** [[paper]](https://arxiv.org/pdf/2108.01547) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/Chinese-darkcyan) ![](https://img.shields.io/badge/Open-purple) ![](https://img.shields.io/badge/2021.08-blue)\n\n    *Hao Zhou, Pei Ke, Zheng Zhang, Yuxian Gu, Yinhe Zheng, Chujie Zheng, Yida Wang, Chen Henry Wu, Hao Sun, Xiaocong Yang, Bosi Wen, Xiaoyan Zhu, Minlie Huang, Jie Tang.*\n  \n  - **EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training.** [[paper]](https://arxiv.org/pdf/2203.09313) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/Chinese-darkcyan) ![](https://img.shields.io/badge/Open-purple) ![](https://img.shields.io/badge/2022.03-blue)\n\n    *Yuxian Gu, Jiaxin Wen, Hao Sun, Yi Song, Pei Ke, Chujie Zheng, Zheng Zhang, Jianzhu Yao, Xiaoyan Zhu, Jie Tang, Minlie Huang.*\n  \n  - **GLM: General Language Model Pretraining with Autoregressive Blank Infilling.** [[paper]](https://aclanthology.org/2022.acl-long.26.pdf) ![](https://img.shields.io/badge/ACL%202022-orange) ![](https://img.shields.io/badge/English%20or%20Chinese-darkcyan) ![](https://img.shields.io/badge/Limited-purple) ![](https://img.shields.io/badge/2021.03-blue)\n\n    *Zhengxiao Du, Yujie Qian, Xiao Liu, Ming Ding, Jiezhong Qiu, Zhilin Yang, Jie Tang.*\n\n  - **GLM-130B: An Open Bilingual Pre-trained Model.** [[paper]](https://openreview.net/pdf?id=-Aw0rrrPUF) ![](https://img.shields.io/badge/ICLR%202023-orange) ![](https://img.shields.io/badge/Multilingual-darkcyan) ![](https://img.shields.io/badge/Open-purple) ![](https://img.shields.io/badge/2022.10-blue)\n\n    *Aohan Zeng, Xiao Liu, Zhengxiao Du, Zihan Wang, Hanyu Lai, Ming Ding, Zhuoyi Yang, Yifan Xu, Wendi Zheng, Xiao Xia, Weng Lam Tam, Zixuan Ma, Yufei Xue, Jidong Zhai, Wenguang Chen, Zhiyuan Liu, Peng Zhang, Yuxiao Dong and Jie Tang.*\n\n  - **ChatGLM.** [[blog]](https://chatglm.cn/blog) ![](https://img.shields.io/badge/Multilingual-darkcyan) ![](https://img.shields.io/badge/Open-purple) ![](https://img.shields.io/badge/2023.03-blue)\n\n- IDEA\n  - **Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence.** [[paper]](https://arxiv.org/pdf/2209.02970) [[blog]](https://idea.edu.cn/fengshenbang-lm.html) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/Open-purple) ![](https://img.shields.io/badge/2022.09-blue)\n\n    *Junjie Wang, Yuxiang Zhang, Lin Zhang, Ping Yang, Xinyu Gao, Ziwei Wu, Xiaoqun Dong, Junqing He, Jianheng Zhuo, Qi Yang, Yongfeng Huang, Xiayu Li, Yanghan Wu, Junyu Lu, Xinyu Zhu, Weifeng Chen, Ting Han, Kunhao Pan, Rui Wang, Hao Wang, Xiaojun Wu, Zhongshen Zeng, Chongpei Chen, Ruyi Gan and Jiaxing Zhang.*\n    - Wenzhong ![](https://img.shields.io/badge/Chinese-darkcyan)\n    - Randeng ![](https://img.shields.io/badge/Chinese-darkcyan)\n    - Yuyuan ![](https://img.shields.io/badge/English-darkcyan)\n    - Zhouwenwang ![](https://img.shields.io/badge/Chinese-darkcyan)\n\n- Huawei\n  - **PanGu-α: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation.** [[paper]](https://arxiv.org/pdf/2104.12369) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/Chinese-darkcyan) ![](https://img.shields.io/badge/Open-purple) ![](https://img.shields.io/badge/2021.04-blue)\n\n    \u003cdetails\u003e\u003csummary\u003eShow Authors\u003c/summary\u003e\u003ci\u003eWei Zeng, Xiaozhe Ren, Teng Su, Hui Wang, Yi Liao, Zhiwei Wang, Xin Jiang, ZhenZhang Yang, Kaisheng Wang, Xiaoda Zhang, Chen Li, Ziyan Gong, Yifan Yao, Xinjing Huang, Jun Wang, Jianfeng Yu, Qi Guo, Yue Yu, Yan Zhang, Jin Wang, Hengtao Tao, Dasen Yan, Zexuan Yi, Fang Peng, Fangqing Jiang, Han Zhang, Lingfeng Deng, Yehong Zhang, Zhe Lin, Chao Zhang, Shaojie Zhang, Mingyue Guo, Shanzhi Gu, Gaojun Fan, Yaowei Wang, Xuefeng Jin, Qun Liu and Yonghong Tian.\u003c/i\u003e\u003c/details\u003e\n  \n  - **PanGu-Bot: Efficient Generative Dialogue Pre-training from Pre-trained Language Model.** [[paper]](https://arxiv.org/pdf/2203.17090) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/Chinese-darkcyan) ![](https://img.shields.io/badge/Closed-purple) ![](https://img.shields.io/badge/2022.03-blue)\n\n    *Fei Mi, Yitong Li, Yulong Zeng, Jingyan Zhou, Yasheng Wang, Chuanfei Xu, Lifeng Shang, Xin Jiang, Shiqi Zhao and Qun Liu.*\n\n- Inspur\n  - **Yuan 1.0: Large-Scale Pre-trained Language Model in Zero-Shot and Few-Shot Learning.** [[paper]](https://arxiv.org/pdf/2110.04725) [[blog]](https://www.inspur.com/lcjtww/445068/445237/2588228/index.html) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/Chinese-darkcyan) ![](https://img.shields.io/badge/Limited-purple) ![](https://img.shields.io/badge/2021.09-blue)\n\n    *Shaohua Wu, Xudong Zhao, Tong Yu, Rongguo Zhang, Chong Shen, Hongli Liu, Feng Li, Hong Zhu, Jiangang Luo, Liang Xu and Xuanwei Zhang.*\n\n- WeChat AI\n  - **WeLM: A Well-Read Pre-trained Language Model for Chinese.** [[paper]](https://arxiv.org/pdf/2209.10372) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/Chinese-darkcyan) ![](https://img.shields.io/badge/Limited-purple) ![](https://img.shields.io/badge/2022.09-blue)\n\n    *Hui Su, Xiao Zhou, Houjin Yu, Yuwen Chen, Zilin Zhu, Yang Yu and Jie Zhou.*\n\n## Analysis\n\u003cdetails\u003e\u003csummary\u003ePreview\u003c/summary\u003e\n\n### Comprehensive\n- **Holistic Evaluation of Language Models.** [[paper]](https://arxiv.org/pdf/2211.09110) [[blog]](https://crfm.stanford.edu/2022/11/17/helm.html) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2022.11-blue)\n\n  \u003cdetails\u003e\u003csummary\u003eShow Authors\u003c/summary\u003e\u003ci\u003ePercy Liang, Rishi Bommasani, Tony Lee, Dimitris Tsipras, Dilara Soylu, Michihiro Yasunaga, Yian Zhang, Deepak Narayanan, Yuhuai Wu, Ananya Kumar, Benjamin Newman, Binhang Yuan, Bobby Yan, Ce Zhang, Christian Cosgrove, Christopher D. Manning, Christopher Ré, Diana Acosta-Navas, Drew A. Hudson, Eric Zelikman, Esin Durmus, Faisal Ladhak, Frieda Rong, Hongyu Ren, Huaxiu Yao, Jue Wang, Keshav Santhanam, Laurel Orr, Lucia Zheng, Mert Yuksekgonul, Mirac Suzgun, Nathan Kim, Neel Guha, Niladri Chatterji, Omar Khattab, Peter Henderson, Qian Huang, Ryan Chi, Sang Michael Xie, Shibani Santurkar, Surya Ganguli, Tatsunori Hashimoto, Thomas Icard, Tianyi Zhang, Vishrav Chaudhary, William Wang, Xuechen Li, Yifan Mai, Yuhui Zhang and Yuta Koreeda.\u003c/i\u003e\u003c/details\u003e\n\n  \u003e Benchmark 30 prominent language models across a wide range of scenarios and for a broad range of metrics to elucidate their capabilities and risks.\n\n- **On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜** [[paper]](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922) ![](https://img.shields.io/badge/FAccT%202021-orange) ![](https://img.shields.io/badge/2021.03-blue)\n\n  *Emily M. Bender, Timnit Gebru, Angelina McMillan-Major and Shmargaret Shmitchell.*\n  \u003e Identified a wide variety of costs and risks associated with the rush for ever larger LMs, including: environmental costs, financial costs, opportunity cost and the risk of substantial harms.\n\n- **TruthfulQA: Measuring How Models Mimic Human Falsehoods.** [[paper]](https://aclanthology.org/2022.acl-long.229.pdf) ![](https://img.shields.io/badge/ACL%202022-orange) ![](https://img.shields.io/badge/2021.09-blue)\n\n  *Stephanie Lin, Jacob Hilton and Owain Evans.*\n  \u003e Models generated many false answers that mimic popular misconceptions and have the potential to deceive humans. The largest models were generally the least truthful.\n\n- **How Much Knowledge Can You Pack Into the Parameters of a Language Model?** [[paper]](https://aclanthology.org/2020.emnlp-main.437.pdf) ![](https://img.shields.io/badge/EMNLP%202020-orange) ![](https://img.shields.io/badge/2020.02-blue)\n\n  *Adam Roberts, Colin Raffel and Noam Shazeer.*\n  \u003e The maximum-likelihood objective used to train our model provides no guarantees as to whether a model will learn a fact or not. This makes it difficult to ensure that the model obtains specific knowledge over the course of pre-training and prevents us from explicitly updating or removing knowledge from a pre-trained model.\n\n- **On the Opportunities and Risks of Foundation Models.** [[paper]](https://arxiv.org/pdf/2108.07258) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2021.08-blue)\n\n  \u003cdetails\u003e\u003csummary\u003eShow Authors\u003c/summary\u003e\u003ci\u003eRishi Bommasani, Drew A. Hudson, Ehsan Adeli, Russ Altman, Simran Arora, Sydney von Arx, Michael S. Bernstein, Jeannette Bohg, Antoine Bosselut, Emma Brunskill, Erik Brynjolfsson, Shyamal Buch, Dallas Card, Rodrigo Castellon, Niladri Chatterji, Annie Chen, Kathleen Creel, Jared Quincy Davis, Dora Demszky, Chris Donahue, Moussa Doumbouya, Esin Durmus, Stefano Ermon, John Etchemendy, Kawin Ethayarajh, Li Fei-Fei, Chelsea Finn, Trevor Gale, Lauren Gillespie, Karan Goel, Noah Goodman, Shelby Grossman, Neel Guha, Tatsunori Hashimoto, Peter Henderson, John Hewitt, Daniel E. Ho, Jenny Hong, Kyle Hsu, Jing Huang, Thomas Icard, Saahil Jain, Dan Jurafsky, Pratyusha Kalluri, Siddharth Karamcheti, Geoff Keeling, Fereshte Khani, Omar Khattab, Pang Wei Koh, Mark Krass, Ranjay Krishna, Rohith Kuditipudi, Ananya Kumar, Faisal Ladhak, Mina Lee, Tony Lee, Jure Leskovec, Isabelle Levent, Xiang Lisa Li, Xuechen Li, Tengyu Ma, Ali Malik, Christopher D. Manning, Suvir Mirchandani, Eric Mitchell, Zanele Munyikwa, Suraj Nair, Avanika Narayan, Deepak Narayanan, Ben Newman, Allen Nie, Juan Carlos Niebles, Hamed Nilforoshan, Julian Nyarko, Giray Ogut, Laurel Orr, Isabel Papadimitriou, Joon Sung Park, Chris Piech, Eva Portelance, Christopher Potts, Aditi Raghunathan, Rob Reich, Hongyu Ren, Frieda Rong, Yusuf Roohani, Camilo Ruiz, Jack Ryan, Christopher Ré, Dorsa Sadigh, Shiori Sagawa, Keshav Santhanam, Andy Shih, Krishnan Srinivasan, Alex Tamkin, Rohan Taori, Armin W. Thomas, Florian Tramèr, Rose E. Wang, William Wang , Bohan Wu, Jiajun Wu, Yuhuai Wu, Sang Michael Xie, Michihiro Yasunaga, Jiaxuan You, Matei Zaharia, Michael Zhang, Tianyi Zhang, Xikun Zhang, Yuhui Zhang, Lucia Zheng, Kaitlyn Zhou and Percy Liang.\u003c/i\u003e\u003c/details\u003e\n\n  \u003e This report provides a thorough account of the opportunities and risks of foundation models, ranging from their capabilities and technical principles to their applications and societal impact.\n\n### Hallucination \u0026 Disinformation\n- **Survey of Hallucination in Natural Language Generation.** [[paper]](https://dl.acm.org/doi/pdf/10.1145/3571730) ![](https://img.shields.io/badge/CSUR%202022-orange) ![](https://img.shields.io/badge/2022.02-blue)\n\n  \u003cdetails\u003e\u003csummary\u003eShow Authors\u003c/summary\u003e\u003ci\u003ePercy Liang, Rishi Bommasani, Tony Lee, Dimitris Tsipras, Dilara Soylu, Michihiro Yasunaga, Yian Zhang, Deepak Narayanan, Yuhuai Wu, Ananya Kumar, Benjamin Newman, Binhang Yuan, Bobby Yan, Ce Zhang, Christian Cosgrove, Christopher D. Manning, Christopher Ré, Diana Acosta-Navas, Drew A. Hudson, Eric Zelikman, Esin Durmus, Faisal Ladhak, Frieda Rong, Hongyu Ren, Huaxiu Yao, Jue Wang, Keshav Santhanam, Laurel Orr, Lucia Zheng, Mert Yuksekgonul, Mirac Suzgun, Nathan Kim, Neel Guha, Niladri Chatterji, Omar Khattab, Peter Henderson, Qian Huang, Ryan Chi, Sang Michael Xie, Shibani Santurkar, Surya Ganguli, Tatsunori Hashimoto, Thomas Icard, Tianyi Zhang, Vishrav Chaudhary, William Wang, Xuechen Li, Yifan Mai, Yuhui Zhang and Yuta Koreeda.\u003c/i\u003e\u003c/details\u003e\n\n  \u003e Benchmark 30 prominent language models across a wide range of scenarios and for a broad range of metrics to elucidate their capabilities and risks.\n\n- **On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?** [[paper]](https://aclanthology.org/2022.naacl-main.387.pdf) ![](https://img.shields.io/badge/NAACL%202022-orange) ![](https://img.shields.io/badge/2022.04-blue)\n\n  *Nouha Dziri, Sivan Milton, Mo Yu, Osmar Zaiane and Siva Reddy.*\n  \u003e Reveals that the standard benchmarks consist of \u003e60% hallucinated responses, leading to models that not only hallucinate but even amplify hallucinations..\n\n- **Generative Language Models and Automated Influence Operations: Emerging Threats and Potential Mitigations.** [[paper]](https://arxiv.org/pdf/2301.04246) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2023.01-blue)\n\n  *Josh A. Goldstein, Girish Sastry, Micah Musser, Renee DiResta, Matthew Gentzel and Katerina Sedova.*\n  \u003e This report aims to assess: how might language models change influence operations, and what steps can be taken to mitigate these threats? This task is inherently speculative, as both AI and influence operations are changing quickly.\n\n- **Forecasting Potential Misuses of Language Models for Disinformation Campaigns—and How to Reduce Risk.** [[blog]](https://openai.com/blog/forecasting-misuse/) ![](https://img.shields.io/badge/2023.01-blue)\n  \u003e OpenAI researchers collaborated with Georgetown University’s Center for Security and Emerging Technology and the Stanford Internet Observatory to investigate how large language models might be misused for disinformation purposes.\n\n- **ChatGPT Wrote a Terrible Gizmodo Article.** [[blog]](https://gizmodo.com/chatgpt-gizmodo-artificial-intelligence-openai-media-1849876066) ![](https://img.shields.io/badge/2022.12-blue)\n  \u003e ChatGPT kept including incorrect information in its explainer—sometimes mixing up basic facts about the history of its own technology.\n\n- **Temporary policy: ChatGPT is banned.** [[blog]](https://meta.stackoverflow.com/questions/421831/temporary-policy-chatgpt-is-banned) ![](https://img.shields.io/badge/2022.12-blue)\n  \u003e While the answers which ChatGPT produces have a high rate of being incorrect, they typically look like they might be good and the answers are very easy to produce.\n\n### Bias \u0026 Toxicity\n- **On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning.** [[paper]](https://arxiv.org/pdf/2212.08061) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2023.12-blue)\n\n  *Omar Shaikh, Hongxin Zhang, William Held, Michael Bernstein and Diyi Yang.*\n  \u003e Find that using zero-shot CoT reasoning in a prompt can significantly increase a model’s likelihood to produce undesirable output.\n\n- **The Woman Worked as a Babysitter: On Biases in Language Generation.** [[paper]](https://aclanthology.org/D19-1339.pdf) ![](https://img.shields.io/badge/EMNLP%202019-orange) ![](https://img.shields.io/badge/2019.09-blue)\n\n  *Emily Sheng, Kai-Wei Chang, Premkumar Natarajan and Nanyun Peng.*\n  \u003e A systematic study of biases in natural language generation (NLG) by analyzing text generated from prompts that contain mentions of different demographic groups.\n\n- **RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models.** [[paper]](https://aclanthology.org/2020.findings-emnlp.301.pdf) ![](https://img.shields.io/badge/EMNLP%202020%20Findings-orange) ![](https://img.shields.io/badge/2020.09-blue)\n\n  *Samuel Gehman, Suchin Gururangan, Maarten Sap, Yejin Choi and Noah A. Smith.*\n  \u003e Using RealToxicityPrompts, we find that pretrained LMs can degenerate into toxic text even from seemingly innocuous prompts.\n\n- **OpenAI's new ChatGPT bot: 10 dangerous things it's capable of.** [[blog]](https://www.bleepingcomputer.com/news/technology/openais-new-chatgpt-bot-10-dangerous-things-its-capable-of/) ![](https://img.shields.io/badge/2022.12-blue)\n  \u003e As the erudite machinery turns into a viral sensation, humans have started to discover some of the AI's biases, like the desire to wipe out humanity.\n### Security Risk\n- **OpwnAI: AI That Can Save the Day or HACK it Away.** [[blog]](https://research.checkpoint.com/2022/opwnai-ai-that-can-save-the-day-or-hack-it-away/) ![](https://img.shields.io/badge/2022.12-blue)\n  \u003e AI models can be used to create a full infection flow, from spear-phishing to running a reverse shell.\n\n- **OpwnAI : Cybercriminals Starting to Use ChatGPT.** [[blog]](https://research.checkpoint.com/2023/opwnai-cybercriminals-starting-to-use-chatgpt/) ![](https://img.shields.io/badge/2023.01-blue)\n  \u003e There are already instances of cybercriminals using OpenAI to develop malicious tools.\n\n- **Security risks of ChatGPT and other AI text generators.** [[blog]](https://www.scmagazine.com/resource/emerging-technology/security-risks-of-chatgpt-and-other-ai-text-generators) ![](https://img.shields.io/badge/2023.01-blue)\n  \u003e Successfully asked ChatGPT to write a convincing phishing email and to create JavaScript that could be used to steal personal information.\n\n- **The security threat of AI-powered cyberattacks.** [[paper]](https://www.traficom.fi/sites/default/files/media/publication/TRAFICOM_The_security_threat_of_AI-enabled_cyberattacks%202022-12-12_en_web.pdf) ![](https://img.shields.io/badge/2022.12-blue)\n\n  *Matti Aksela, Samuel Marchal, Andrew Patel, Lina Rosenstedt and WithSecure.*\n  \u003e Investigate the security threat of AI-enabled cyberattacks by summarising current knowledge on the topic.\n\n- **How hackers might be exploiting ChatGPT.** [[blog]](https://cybernews.com/security/hackers-exploit-chatgpt/) ![](https://img.shields.io/badge/2023.01-blue)\n  \u003e The viral AI chatbot ChatGPT might advise threat actors how to hack into networks with ease.\n\n### LM Attack\n- **Extracting Training Data from Large Language Models.** [[paper]](https://arxiv.org/pdf/2012.07805) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2020.12-blue)\n\n  *Nicholas Carlini, Florian Tramer, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom Brown, Dawn Song, Ulfar Erlingsson, Alina Oprea and Colin Raffel.*\n  \u003e This paper demonstrates that an adversary can perform a training data extraction attack to recover individual training examples by querying the language model.\n\n- **Ignore Previous Prompt: Attack Techniques For Language Models.** [[paper]](https://openreview.net/pdf?id=qiaRo_7Zmug) ![](https://img.shields.io/badge/NeurIPS%202022%20Workshop-orange) ![](https://img.shields.io/badge/2022.11-blue)\n\n  *Fábio Perez and Ian Ribeiro.*\n  \u003e Study prompt injection attacks against LLMs and propose a framework to explore such attacks; Investigate two specific attacks: goal hijacking and prompt leaking.\n\n### Environment\n- **Carbon Emissions and Large Neural Network Training.** [[paper]](https://arxiv.org/pdf/2104.10350) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2021.04-blue)\n\n  *David Patterson, Joseph Gonzalez, Quoc Le, Chen Liang, Lluis-Miquel Munguia, Daniel Rothchild, David So, Maud Texier and Jeff Dean.*\n  \u003e Calculate the energy use and carbon footprint of several recent large models-T5, Meena, GShard, Switch Transformer, and GPT-3.\n\u003e \u003c/details\u003e\n\n## Detection\n### Papers\n#### Survey\n- **Automatic Detection of Machine Generated Text: A Critical Survey.** [[paper]](https://aclanthology.org/2020.coling-main.208.pdf) ![](https://img.shields.io/badge/COLING%202020-orange) ![](https://img.shields.io/badge/2020.11-blue)\n\n  *Ganesh Jawahar, Muhammad Abdul-Mageed and Laks V.S. Lakshmanan.*\n\n- **在线社交网络文本内容对抗技术.** [[paper]](http://cjc.ict.ac.cn/online/onlinepaper/lxm-202286133102.pdf) ![](https://img.shields.io/badge/计算机学报%202022-orange) ![](https://img.shields.io/badge/2022.08-blue)\n\n  *刘晓明, 张兆晗, 杨晨阳, 张宇辰, 沈超, 周亚东 and 管晓宏.*\n\n- **Synthetic Text Detection: Systemic Literature Review.** [[paper]](https://arxiv.org/pdf/2210.06336) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2022.10-blue)\n\n  *Jesus Guerrero, Izzat Alsmadi.*\n\n- **Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods.** [[paper]](https://arxiv.org/pdf/2210.07321) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2022.10-blue)\n\n  *Evan Crothers, Nathalie Japkowicz and Herna Viktor.*\n\n- **Deepfake Text Detection: Limitations and Opportunities.** [[paper]](https://arxiv.org/pdf/2210.09421) ![](https://img.shields.io/badge/S\u0026P%202023-orange) ![](https://img.shields.io/badge/2022.10-blue)\n\n  *Jiameng Pu, Zain Sarwar, Sifat Muhammad Abdullah, Abdullah Rehman, Yoonjin Kim, Parantapa Bhattacharya, Mobin Javed and Bimal Viswanath.*\n\n- **The Science of Detecting LLM-Generated Texts.** [[paper]](https://arxiv.org/pdf/2303.07205) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2023.02-blue)\n\n  *Ruixiang Tang, Yu-Neng Chuang and Xia Hu.*\n\n- **To ChatGPT, or not to ChatGPT: That is the question!** [[paper]](https://arxiv.org/pdf/2304.01487) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2023.04-blue)\n\n  *Alessandro Pegoraro, Kavita Kumari, Hossein Fereidooni and Ahmad-Reza Sadeghi.*\n\n- **The Age of Synthetic Realities: Challenges and Opportunities.** [[paper]](https://arxiv.org/pdf/2306.11503) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2023.06-blue)\n\n  *João Phillipe Cardenuto, Jing Yang, Rafael Padilha, Renjie Wan, Daniel Moreira, Haoliang Li, Shiqi Wang, Fernanda Andaló, Sébastien Marcel and Anderson Rocha.*\n\n- **Attribution and Obfuscation of Neural Text Authorship: A Data Mining Perspective.** [[paper]](https://dl.acm.org/doi/pdf/10.1145/3606274.3606276) ![](https://img.shields.io/badge/ACM%20SIGKDD%20Explorations%20Newsletter-orange) ![](https://img.shields.io/badge/2023.07-blue)\n\n  *Adaku Uchendu, Thai Le and Dongwon Lee.*\n\n- **Detecting Artificial Intelligence: A New Cyberarms Race Begins.** [[paper]](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\u0026arnumber=10206065) ![](https://img.shields.io/badge/Computer%202023-orange) ![](https://img.shields.io/badge/2023.08-blue)\n\n  *Mark Campbell and Mlađan Jovanović.*\n\n- **Detecting ChatGPT: A Survey of the State of Detecting ChatGPT-Generated Text.** [[paper]](https://arxiv.org/pdf/2309.07689.pdf) ![](https://img.shields.io/badge/RANLP%202023%20Workshop-orange) ![](https://img.shields.io/badge/2023.08-blue)\n\n  *Mahdi Dhaini, Wessel Poelman and Ege Erdogan.*\n\n- **A Survey on LLM-gernerated Text Detection: Necessity, Methods, and Future Directions.** [[paper]](https://arxiv.org/pdf/2310.14724.pdf) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2023.10-blue)\n\n  *Junchao Wu, Shu Yang, Runzhe Zhan, Yulin Yuan, Derek F. Wong and Lidia S. Chao.*\n\n- **Towards Possibilities \u0026 Impossibilities of AI-generated Text Detection: A Survey.** [[paper]](https://arxiv.org/pdf/2310.15264.pdf) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2023.10-blue)\n\n  *Soumya Suvra Ghosal, Souradip Chakraborty, Jonas Geiping, Furong Huang, Dinesh Manocha and Amrit Singh Bedi.*\n\n- **A Survey on Detection of LLMs-Generated Content.** [[paper]](https://arxiv.org/pdf/2310.15654.pdf) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2023.10-blue)\n\n  *Xianjun Yang, Liangming Pan, Xuandong Zhao, Haifeng Chen, Linda Petzold, William Yang Wang and Wei Cheng.*\n\n- **A Survey of Text Watermarking in the Era of Large Language Models.** [[paper]](https://arxiv.org/pdf/2312.07913.pdf) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2023.12-blue)\n\n  *Aiwei Liu, Leyi Pan, Yijian Lu, Jingjing Li, Xuming Hu, Lijie Wen, Irwin King and Philip S. Yu.*\n\n- **Detection of Machine-Generated Text: Literature Survey.** [[paper]](https://arxiv.org/pdf/2402.01642.pdf) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2024.01-blue)\n\n  *Dmytro Valiaiev.*\n\n- **Detecting Multimedia Generated by Large AI Models: A Survey.** [[paper]](https://arxiv.org/pdf/2402.00045.pdf) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2024.01-blue)\n\n  *Li Lin, Neeraj Gupta, Yue Zhang, Hainan Ren, Chun-Hao Liu, Feng Ding, Xin Wang, Xin Li, Luisa Verdoliva and Shu Hu.*\n\n- **Copyright Protection in Generative AI: A Technical Perspective.** [[paper]](https://arxiv.org/pdf/2402.02333.pdf) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2024.02-blue)\n\n  *Jie Ren, Han Xu, Pengfei He, Yingqian Cui, Shenglai Zeng, Jiankun Zhang, Hongzhi Wen, Jiayuan Ding, Hui Liu, Yi Chang and Jiliang Tang.*\n\n- **Beyond the Human Eye: Comprehensive Approaches to AI Text Detection.** [[paper]](https://www.researchgate.net/profile/Yuksel-Celik-2/publication/377930230_Beyond_the_Human_Eye_Comprehensive_Approaches_to_AI_Text_Detection_18th_Annual_Symposium_on_Information_Assurance_ASIA_'23_53_Beyond_the_Human_Eye_Comprehensive_Approaches_to_AI_Text_Detection/links/65bdc39a1e1ec12eff6cf935/Beyond-the-Human-Eye-Comprehensive-Approaches-to-AI-Text-Detection-18th-Annual-Symposium-on-Information-Assurance-ASIA-23-53-Beyond-the-Human-Eye-Comprehensive-Approaches-to-AI-Text-Detection.pdf?_tp=eyJjb250ZXh0Ijp7ImZpcnN0UGFnZSI6InB1YmxpY2F0aW9uIiwicGFnZSI6InB1YmxpY2F0aW9uIn19) ![](https://img.shields.io/badge/ASIA%202023-orange) ![](https://img.shields.io/badge/2024.02-blue)\n\n  *Jamal Goddard, Yuksel Celik and Sanjay Goel.*\n\n- **A Survey of AI-generated Text Forensic Systems: Detection, Attribution, and Characterization.** [[paper]](https://arxiv.org/pdf/2403.01152.pdf) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2024.03-blue)\n\n  *Tharindu Kumarage, Garima Agrawal, Paras Sheth, Raha Moraffah, Aman Chadha, Joshua Garland and Huan Liu.*\n\n- **Decoding the AI Pen: Techniques and Challenges in Detecting AI-Generated Text.** [[paper]](https://arxiv.org/pdf/2403.05750) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2024.03-blue)\n\n  *Sara Abdali, Richard Anarfi, CJ Barberan and Jia He.*\n\n- **Detecting AI-Generated Text: Factors Influencing Detectability with Current Methods.** [[paper]](https://arxiv.org/pdf/2406.15583) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2024.06-blue)\n\n  *Kathleen C. Fraser, Hillary Dawkins and Svetlana Kiritchenko.*\n\n- **From Intentions to Techniques: A Comprehensive Taxonomy and Challenges in Text Watermarking for Large Language Models.** [[paper]](https://arxiv.org/pdf/2406.11106) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2024.06-blue)\n\n  *Harsh Nishant Lalai, Aashish Anantha Ramakrishnan, Raj Sanjay Shah and Dongwon Lee.*\n\n- **Survey on Plagiarism Detection in Large Language Models: The Impact of ChatGPT and Gemini on Academic Integrity.** [[paper]](https://arxiv.org/pdf/2407.13105) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2024.06-blue)\n\n  *Shushanta Pudasaini, Luis Miralles-Pechuán, David Lillis and Marisa Llorens Salvador.*\n\n- **Survey for Detecting AI-generated Content.** [[paper]](https://madison-proceedings.com/index.php/aetr/article/view/2542/2563) ![](https://img.shields.io/badge/CVMARS%202024-orange) ![](https://img.shields.io/badge/2024.07-blue)\n\n  *Yu Wang, Ziyan Wang.*\n\n- **Building Intelligence Identification System via Large Language Model Watermarking: A Survey and Beyond.** [[paper]](https://arxiv.org/pdf/2407.11100) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2024.07-blue)\n\n  *Xuhong Wang, Haoyu Jiang, Yi Yu, Jingru Yu, Yilun Lin, Ping Yi, Yingchun Wang, Yu Qiao, Li Li and Fei-Yue Wang.*\n\n- **Authorship Attribution in the Era of LLMs: Problems, Methodologies, and Challenges.** [[paper]](https://arxiv.org/pdf/2408.08946) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2024.08-blue)\n\n  *Baixiang Huang, Canyu Chen and Kai Shu.*\n\n- **SoK: Watermarking for AI-Generated Content.** [[paper]](https://arxiv.org/pdf/2411.18479) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2024.11-blue)\n\n  *Xuandong Zhao, Sam Gunn, Miranda Christ, Jaiden Fairoze, Andres Fabrega, Nicholas Carlini, Sanjam Garg, Sanghyun Hong, Milad Nasr, Florian Tramer, Somesh Jha, Lei Li, Yu-Xiang Wang and Dawn Song.*\n\n#### Human Detection\n- **Deepfake Bot Submissions to Federal Public Comment Websites Cannot Be Distinguished from Human Submissions.** [[paper]](https://techscience.org/a/2019121801/download) ![](https://img.shields.io/badge/Technology%20Science%202019-orange) ![](https://img.shields.io/badge/2019.12-blue)\n\n  *Max Weiss.*\n  \u003e Generate and submit 1,001 deepfake comments regarding a Medicaid reform waiver to a federal public comment website. The human classification results are no better than would have been gotten by random guessing.\n\n- **RoFT: A Tool for Evaluating Human Detection of Machine-Generated Text.** [[paper]](https://aclanthology.org/2020.emnlp-demos.25.pdf) ![](https://img.shields.io/badge/EMNLP%202020-orange) ![](https://img.shields.io/badge/2020.10-blue)\n\n  *Liam Dugan, Daphne Ippolito, Arun Kirubarajan and Chris Callison-Burch.*\n  \u003e Develop the Real or Fake Text (RoFT) system, a novel application for simultaneously collecting quality annotations of machinegenerated text while allowing the public to assess and improve their skill at detecting machinegenerated text.\n\n- **All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text.** [[paper]](https://aclanthology.org/2021.acl-long.565.pdf) ![](https://img.shields.io/badge/ACL%202021-orange) ![](https://img.shields.io/badge/2021.06-blue)\n\n  *Elizabeth Clark, Tal August, Sofia Serrano, Nikita Haduong, Suchin Gururangan and Noah A. Smith.*\n  \u003e Assess nonexperts’ ability to distinguish between humanand machine-authored text, and test three evaluator-training methods to see if we could improve people’s ability to identify machinegenerated text.\n\n- **Human Heuristics for AI-Generated Language Are Flawed.** [[paper]](https://arxiv.org/pdf/2206.07271) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2022.06-blue)\n\n  *Maurice Jakesch, Jeffrey Hancock and Mor Naaman.*\n  \u003e Study how humans discern whether verbal self-presentations were generated by AI. Show that human judgments of AI-generated language are handicapped by intuitive but flawed heuristics.\n\n- **Real or Fake Text?: Investigating Human Ability to Detect Boundaries Between Human-Written and Machine-Generated Text.** [[paper]](https://arxiv.org/pdf/2212.12672) ![](https://img.shields.io/badge/AAAI%202023-orange) ![](https://img.shields.io/badge/2022.12-blue)\n\n  *Liam Dugan, Daphne Ippolito, Arun Kirubarajan, Sherry Shi and Chris Callison-Burch.*\n  \u003e Analyze how a variety of variables (model size, decoding strategy, fine-tuning, prompt genre, etc.) affect human detection performance.\n\n- **AI model GPT-3 (dis)informs us better than humans.** [[paper]](https://arxiv.org/pdf/2301.11924) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2023.01-blue)\n\n  *Giovanni Spitale, Nikola Biller-Andorno and Federico Germani.*\n  \u003e Evaluate whether recruited individuals can distinguish disinformation from accurate information, and determine whether a tweet has been written by a Twitter user or by GPT-3.\n\n- **Creating a Large Language Model of a Philosopher.** [[paper]](https://arxiv.org/pdf/2302.01339) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2023.02-blue)\n\n  *Eric Schwitzgebel, David Schwitzgebel and Anna Strasser.*\n  \u003e Fine-tuned the GPT-3 on the corpus of Daniel Dennett, then asked it a series of philosophical questions. Ordinary research participants untrained in philosophy were at or near chance in distinguishing GPT-3’s answers from those of an “actual human philosopher”. .\n\n- **Does Human Collaboration Enhance the Accuracy of Identifying LLM-Generated Deepfake Texts?** [[paper]](https://arxiv.org/pdf/2304.01002) ![](https://img.shields.io/badge/HCOMP%202023-orange) ![](https://img.shields.io/badge/2023.04-blue)\n\n  *Adaku Uchendu, Jooyoung Lee, Hua Shen, Thai Le, Ting-Hao 'Kenneth' Huang and Dongwon Lee.*\n  \u003e Find that: (1) expert humans detect deepfake texts significantly better than non-expert humans, (2) synchronous teams on the Upwork detect deepfake texts significantly better than individuals, while asynchronous teams on the AMT detect deepfake texts weakly better than individuals, and (3) among various error categories, examining coherence and consistency in texts is useful in detecting deepfake texts.\n\n- **Too Good to Be True? An Empirical Study of ChatGPT Capabilities for Academic Writing and Implications for Academic Misconduct.** [[paper]](https://www.researchgate.net/profile/Peter-Andre-Busch/publication/370106469_Too_Good_to_Be_True_An_Empirical_Study_of_ChatGPT_Capabilities_for_Academic_Writing_and_Implications_for_Academic_Misconduct/links/64403aa91b8d044c6335d7ce/Too-Good-to-Be-True-An-Empirical-Study-of-ChatGPT-Capabilities-for-Academic-Writing-and-Implications-for-Academic-Misconduct.pdf) ![](https://img.shields.io/badge/AMCIS%202023-orange) ![](https://img.shields.io/badge/2023.04-blue)\n\n  *Peter André Busch and Geir Inge Hausvik.*\n  \u003e Ask 15 faculty members to assess a total of ten answers (two each) to an actual IS exam question, of which students wrote five, and ChatGPT generated five. Find that ChatGPT can generate answers of generally good quality that may pass as human-written text by examiners.\n\n- **Game of Tones: Faculty detection of GPT-4 generated content in university assessments.** [[paper]](https://arxiv.org/pdf/2305.18081) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2023.05-blue)\n\n  *Mike Perkins, Jasper Roe, Darius Postma, James McGaughran and Don Hickerson.*\n  \u003e This study explores the robustness of university assessments against the use of Open AI's Generative Pre-Trained Transformer 4 (GPT-4) generated content and evaluates the ability of academic staff to detect its use when supported by the Turnitin Artificial Intelligence (AI) detection tool.\n\n- **The Unseen A+ Student: Navigating the Impact of Large Language Models in the Classroom.** [[paper]](https://openreview.net/pdf?id=9ZKJLYg5EQ) ![](https://img.shields.io/badge/ICML%202023%20Workshop-orange) ![](https://img.shields.io/badge/2023.05-blue)\n\n  *Matyas Bohacek.*\n  \u003e Collect a dataset of authentic high school coursework and generate their AI alternatives and text continuations using ChatGPT with 4.0, 3.5, and 3.5 Legacy backbones. Through a study involving student peers, we found that ChatGPT can quickly produce high-school-level coursework that peers consider better than human-written text, even in a low-resourced language like Czech. Moreover, show that the AI text detectors fail to identify these texts in Czech.\n\n- **Can linguists distinguish between ChatGPT/AI and human writing?: A study of research ethics and academic publishing.** [[paper]](https://www.sciencedirect.com/science/article/pii/S2772766123000289/pdfft?md5=40e5bb4675092f7b0002d6a91c84d79b\u0026pid=1-s2.0-S2772766123000289-main.pdf) ![](https://img.shields.io/badge/Research%20Methods%20in%20Applied%20Linguistics%202023-orange) ![](https://img.shields.io/badge/2023.08-blue)\n\n  *J. Elliott Casal and Matt Kessler.*\n  \u003e Investigate: 1) the extent to which linguists/reviewers from top journals can distinguish AI- from human-generated writing, 2) what the basis of reviewers’ decisions are, and 3) the extent to which editors of top Applied Linguistics journals believe AI tools are ethical for research purposes.\n\n- **Detection of GPT-4 Generated Text in Higher Education: Combining Academic Judgement and Software to Identify Generative AI Tool Misuse.** [[paper]](https://link.springer.com/content/pdf/10.1007/s10805-023-09492-6.pdf) ![](https://img.shields.io/badge/Journal%20of%20Academic%20Ethics%202023-orange) ![](https://img.shields.io/badge/2023.10-blue)\n\n  *Mike Perkins, Jasper Roe, Darius Postma, James McGaughran and Don Hickerson.*\n  \u003e Explore the capability of academic staff assisted by the Turnitin Artificial Intelligence (AI) detection tool to identify the use of AI-generated content in university assessments.\n\n- **ChatGPT versus Human Essayists: An Exploration of the Impact of Artificial Intelligence for Authorship and Academic Integrity in the Humanities.** [[paper]](https://www.researchsquare.com/article/rs-3483059/v1.pdf?c=1699337517000) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2023.11-blue)\n\n  *Tom Revell, Will Yeadon, Glenn Cahilly-Bretzin, Isabella Clarke, George Manning, Jasmine Jones, Clare Mulley, Rafael Pascual, Natasha Bradley, Daniel Thomas and Francis Leneghan.*\n  \u003e Examine AI’s ability to write essays analysing Old English poetry; human markers assessed and attempted to distinguish them from authentic analyses of poetry by first-year undergraduate students in English at the University of Oxford.\n\n- **Evaluating AI and Human Authorship Quality in Academic Writing through Physics Essays.** [[paper]](https://arxiv.org/pdf/2403.05458) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2024.03-blue)\n\n  *Will Yeadon, Elise Agra, Oto-obong Inyang, Paul Mackay and Arin Mizouri.*\n  \u003e Evaluate n=300 short-form physics essay submissions, equally divided between student work submitted before the introduction of ChatGPT and those generated by OpenAI's GPT-4. In blinded evaluations conducted by five independent markers who were unaware of the origin of the essays, we observed no statistically significant differences in scores between essays authored by humans and those produced by AI (p-value =0.107, α = 0.05).\n\n- **A feasibility study for the application of AI-generated conversations in pragmatic analysis.** [[paper]](https://www.sciencedirect.com/science/article/pii/S0378216624000092/pdfft?md5=05a53e7d33ee35c05c424175cdadb98f\u0026pid=1-s2.0-S0378216624000092-main.pdf) ![](https://img.shields.io/badge/Journal%20of%20Pragmatics-orange) ![](https://img.shields.io/badge/2024.04-blue)\n\n  *Xi Chen, Jun Li and Yuting Ye.*\n  \u003e Compare 148 ChatGPT-generated conversations with 82 human-written ones and 354 human evaluations of these conversations. The data are analysed using various methods, including traditional speech strategy coding, four computational methods developed in NLP, and four statistical tests.\n\n- **People cannot distinguish GPT-4 from a human in a Turing test.** [[paper]](https://arxiv.org/pdf/2405.08007) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2024.05-blue)\n\n  *Cameron R. Jones and Benjamin K. Bergen.*\n  \u003e Evaluate 3 systems (ELIZA, GPT-3.5 and GPT-4) in a randomized, controlled, and preregistered Turing test. Human participants had a 5 minute conversation with either a human or an AI, and judged whether or not they thought their interlocutor was human. GPT-4 was judged to be a human 54% of the time, outperforming ELIZA (22%) but lagging behind actual humans (67%).\n\n- **Can human intelligence safeguard against artificial intelligence? Exploring individual differences in the discernment of human from AI texts.** [[paper]](https://www.researchsquare.com/article/rs-4277893/v1.pdf?c=1714412829000) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2024.04-blue)\n\n  *Jason Chein, Steven Martinez and Alexander Barone.*\n  \u003e Examine individual differences in the human ability to differentiate human- from AI-generated texts, exploring relationships with fluid intelligence, executive functioning, empathy, and digital habits. Overall, participants exhibited better than chance text discrimination, with substantial variation across individuals.\n\n- **Limitations of Human Identification of Automatically Generated Text.** [[paper]](https://aclanthology.org/2024.lrec-main.919.pdf) ![](https://img.shields.io/badge/LREC--COLING%202024-orange) ![](https://img.shields.io/badge/2024.05-blue)\n\n  *Nadège Alavoine, Maximin Coavoux, Emmanuelle Esperança-Rodier, Romane Gallienne, Carlos Gonzalez Gallardo, Jérôme Goulian, Jose G. Moreno, Aurélie Névéol, Didier Schwab, Vincent Segonne and Johanna Simoens.*\n  \u003e Propose a new corpus in French and English for the task of recognising automatically generated texts and conduct a study of how humans perceive the text. The results show that the generated texts by tools such as ChatGPT share some common characteristics but they are not clearly identifiable which generates different perceptions of these texts.\n\n- **Seeing Through AI's Lens: Enhancing Human Skepticism Towards LLM-Generated Fake News.** [[paper]](https://arxiv.org/pdf/2406.14012) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2024.06-blue)\n\n  *Navid Ayoobi, Sadat Shahriar and Arjun Mukherjee.*\n  \u003e By providing cues in human-written and LLM-generated news, we can help individuals increase their skepticism towards fake LLM-generated news. This paper aims to elucidate simple markers that help individuals distinguish between articles penned by humans and those created by LLMs. Devise a metric named Entropy-Shift Authorship Signature (ESAS) based on the information theory and entropy principles.\n\n- **GPT-4 is judged more human than humans in displaced and inverted Turing tests.** [[paper]](https://arxiv.org/pdf/2407.08853) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2024.07-blue)\n\n  *Ishika Rathi, Sydney Taylor, Benjamin K. Bergen and Cameron R. Jones.*\n  \u003e Measure how well people and large language models can discriminate using two modified versions of the Turing test: inverted and displaced. GPT-3.5, GPT-4, and displaced human adjudicators judged whether an agent was human or AI on the basis of a Turing test transcript. Suggest that both humans and current LLMs struggle to distinguish between the two when they are not actively interrogating the person, underscoring an urgent need for more accurate tools to detect AI in conversations.\n\n#### Automatic Detection\n- **Defending Against Neural Fake News.** [[paper]](https://proceedings.neurips.cc/paper/2019/file/3e9f0fc9b2f89e043bc6233994dfcf76-Paper.pdf) ![](https://img.shields.io/badge/NeurIPS%202019-orange) ![](https://img.shields.io/badge/2019.05-blue)\n\n  *Rowan Zellers, Ari Holtzman, Hannah Rashkin, Yonatan Bisk, Ali Farhadi, Franziska Roesner and Yejin Choi.*\n  \u003e Present a model for controllable text generation called Grover. Find that the best way to detect neural fake news is to use a model that is also a generator.\n\n- **GLTR: Statistical Detection and Visualization of Generated Text.** [[paper]](https://aclanthology.org/P19-3019.pdf) ![](https://img.shields.io/badge/ACL%202019-orange) ![](https://img.shields.io/badge/2019.06-blue)\n\n  *Sebastian Gehrmann, Hendrik Strobelt and Alexander M. Rush.*\n  \u003e A Giant Language model Test Room. GLTR aims to both teach users what to be aware of when assessing whether a text is real, and to assist them in performing forensic analyses.\n\n- **Real or Fake? Learning to Discriminate Machine from Human Generated Text.** [[paper]](https://arxiv.org/pdf/1906.03351) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2019.06-blue)\n\n  *Anton Bakhtin, Sam Gross, Myle Ott, Yuntian Deng, Marc'Aurelio Ranzato and Arthur Szlam.*\n  \u003e Use Energy-based models to discriminate real text from text generated by the auto-regressive models.\n\n- **The Limitations of Stylometry for Detecting Machine-Generated Fake News.** [[paper]](https://direct.mit.edu/coli/article-pdf/46/2/499/1847559/coli_a_00380.pdf) ![](https://img.shields.io/badge/Computational%20Linguistics%202020-orange) ![](https://img.shields.io/badge/2019.08-blue)\n\n  *Tal Schuster, Roei Schuster, Darsh J Shah and Regina Barzilay.*\n  \u003e Examine the state-of-the-art stylometry model, and find it effective in preventing impersonation, but limited in detecting LM-generated misinformation.\n\n- **Automatic Detection of Generated Text is Easiest when Humans are Fooled.** [[paper]](https://aclanthology.org/2020.acl-main.164.pdf) ![](https://img.shields.io/badge/ACL%202020-orange) ![](https://img.shields.io/badge/2019.11-blue)\n\n  *Daphne Ippolito, Daniel Duckworth, Chris Callison-Burch and Douglas Eck.*\n  \u003e A comprehensive study of generated text detection systems’ sensitivity to model structure, decoding strategy, and excerpt length.\n\n- **Reverse Engineering Configurations of Neural Text Generation Models.** [[paper]](https://aclanthology.org/2020.acl-main.25.pdf) ![](https://img.shields.io/badge/ACL%202020-orange) ![](https://img.shields.io/badge/2020.04-blue)\n\n  *Yi Tay, Dara Bahri, Che Zheng, Clifford Brunk, Donald Metzler and Andrew Tomkins.*\n  \u003e Propose the new task of distinguishing which of several variants (e.g., sampling methods, top-k probabilities, model architectures, etc.) of a given model generated some piece of text. Find that detectable artifacts are present and that different modeling choices can be inferred by looking at generated text alone.\n\n- **TweepFake: about Detecting Deepfake Tweets.** [[paper]](https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0251415\u0026type=printable) ![](https://img.shields.io/badge/PLoS%20ONE%202021-orange) ![](https://img.shields.io/badge/2020.07-blue)\n\n  *Tiziano Fagni, Fabrizio Falchi, Margherita Gambini, Antonio Martella and Maurizio Tesconi.*\n  \u003e Collect the first dataset of real deepfake tweets, TweepFake. Evaluate 13 deepfake text detection methods.\n\n- **Identifying Automatically Generated Headlines using Transformers.** [[paper]](https://aclanthology.org/2021.nlp4if-1.1.pdf) ![](https://img.shields.io/badge/NAACL%202021%20Workshop-orange) ![](https://img.shields.io/badge/2020.09-blue)\n\n  *Antonis Maronikolakis, Hinrich Schutze and Mark Stevenson.*\n  \u003e Create a dataset containing human and computer-generated headlines. Transformers achieved an overall accuracy of 85.7%.\n\n- **Detecting Cross-Modal Inconsistency to Defend Against Neural Fake News.** [[paper]](https://aclanthology.org/2020.emnlp-main.163.pdf) ![](https://img.shields.io/badge/EMNLP%202020-orange) ![](https://img.shields.io/badge/2020.09-blue)\n\n  *Reuben Tan, Bryan A. Plummer and Kate Saenko.*\n  \u003e Present DIDAN, a approach which exploits possible semantic inconsistencies between the text and image/captions to detect machine-generated articles.\n\n- **Neural Deepfake Detection with Factual Structure of Text.** [[paper]](https://aclanthology.org/2020.emnlp-main.193.pdf) ![](https://img.shields.io/badge/EMNLP%202020-orange) ![](https://img.shields.io/badge/2020.10-blue)\n\n  *Wanjun Zhong, Duyu Tang, Zenan Xu, Ruize Wang, Nan Duan, Ming Zhou, Jiahai Wang and Jian Yin.*\n  \u003e Propose a graph-based model that utilizes the factual structure of a document for deepfake detection of text.\n\n- **Authorship Attribution for Neural Text Generation.** [[paper]](https://aclanthology.org/2020.emnlp-main.673.pdf) ![](https://img.shields.io/badge/EMNLP%202020-orange) ![](https://img.shields.io/badge/2020.11-blue)\n\n  *Adaku Uchendu, Thai Le, Kai Shu and Dongwon Lee.*\n  \u003e Investigate the authorship attribution problem in three versions: (1) given two texts T1 and T2, are both generated by the same method or not? (2) is the given text T written by a human or machine? (3) given a text T and k candidate neural methods, can we single out the method (among k alternatives) that generated T?\n\n- **How Effectively Can Machines Defend Against Machine-Generated Fake News? An Empirical Study.** [[paper]](https://aclanthology.org/2020.insights-1.7.pdf) ![](https://img.shields.io/badge/EMNLP%202020%20Workshop-orange) ![](https://img.shields.io/badge/2020.11-blue)\n\n  *Meghana Moorthy Bhat and Srinivasan Parthasarathy.*\n  \u003e Measure the performance of models by looking at accuracy with respect to perturbations introduced in this work. Find that success of style-based classifiers are limited when real articles are perturbed even under extreme modifications.\n\n- **Feature-based detection of automated language models: tackling GPT-2, GPT-3 and Grover.** [[paper]](https://peerj.com/articles/cs-443.pdf) ![](https://img.shields.io/badge/PeerJ%20Computer%20Science%202021-orange) ![](https://img.shields.io/badge/2021.04-blue)\n\n  *Leon Fröhling and Arkaitz Zubiaga.*\n  \u003e A feature-based detection approach relies on features that discriminate between human and machine text by modelling properties and dimensions in which both types of text differ.\n\n- **Detecting Bot-Generated Text by Characterizing Linguistic Accommodation in Human-Bot Interactions.** [[paper]](https://aclanthology.org/2021.findings-acl.286.pdf) ![](https://img.shields.io/badge/ACL%202021%20Findings-orange) ![](https://img.shields.io/badge/2021.06-blue)\n\n  *Paras Bhatt and Anthony Rios.*\n  \u003e Show that bot-generated text detection methods are more robust across datasets and models if we use information about how people respond to it rather than using the bot’s text directly.\n\n- **Artificial Text Detection via Examining the Topology of Attention Maps.** [[paper]](https://aclanthology.org/2021.emnlp-main.50v2.pdf) ![](https://img.shields.io/badge/EMNLP%202021-orange) ![](https://img.shields.io/badge/2021.09-blue)\n\n  *Laida Kushnareva, Daniil Cherniavskii, Vladislav Mikhailov, Ekaterina Artemova, Serguei Barannikov, Alexander Bernstein, Irina Piontkovskaya, Dmitri Piontkovski and Evgeny Burnaev.*\n  \u003e Propose three novel types of interpretable topological features based on Topological Data Analysis (TDA). The features derived from the BERT model outperform count- and neural-based baselines up to 10% on three common datasets, and tend to be the most robust towards unseen GPT-style generation models as opposed to existing methods.\n\n- **Unsupervised and Distributional Detection of Machine-Generated Text.** [[paper]](https://arxiv.org/pdf/2111.02878) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2021.11-blue)\n\n  *Matthias Gallé, Jos Rozen, Germán Kruszewski and Hady Elsahar.*\n  \u003e Propose a method to detect those machine-generated documents leveraging repeated higher-order n-grams, which we show over-appear in machine-generated text as compared to human ones.\n\n- **Detecting computer-generated disinformation.** [[paper]](https://link.springer.com/content/pdf/10.1007/s41060-021-00299-5.pdf) ![](https://img.shields.io/badge/IJDSA%202022-orange) ![](https://img.shields.io/badge/2021.12-blue)\n\n  *Harald Stiff and Fredrik Johansson.*\n  \u003e Evaluate promising Transformer-based detection algorithms in a large variety of experiments involving both in-distribution and out-of-distribution test data, as well as evaluation on more realistic in-the-wild data.\n\n- **On pushing DeepFake Tweet Detection capabilities to the limits.** [[paper]](https://dl.acm.org/doi/pdf/10.1145/3501247.3531560) ![](https://img.shields.io/badge/WebSci%202022-orange) ![](https://img.shields.io/badge/2022.06-blue)\n\n  *Margherita Gambini, Tiziano Fagni, Fabrizio Falchi and Maurizio Tesconi.*\n  \u003e Study and improve the performance of the stateof-the-art deepfake tweet detection methods over GPT-2 tweets and the detectors’ capabilities to generalize over tweets generated by GPT-3.\n\n- **Cross-Domain Detection of GPT-2-Generated Technical Text.** [[paper]](https://aclanthology.org/2022.naacl-main.88.pdf) ![](https://img.shields.io/badge/NAACL%202022-orange) ![](https://img.shields.io/badge/2022.07-blue)\n\n  *Juan Rodriguez, Todd Hay, David Gros, Zain Shamsi and Ravi Srinivasan.*\n  \u003e Find that RoBERTa-based detectors can be successfully adapted from one scientific discipline (physics) to another (biomedicine), requiring relatively small amounts of in-domain labeled data.\n\n- **Automatic Detection of Machine Generated Texts: Need More Tokens.** [[paper]](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\u0026arnumber=9983964) ![](https://img.shields.io/badge/IVMEM%202022-orange) ![](https://img.shields.io/badge/2022.09-blue)\n\n  *Paras Bhatt and Anthony Rios.*\n  \u003e Present a dataset for Russian language and conduct a set of learning experiments to build accurate machine-generated text detectors for both English and Russian languages.\n\n- **Threat Scenarios and Best Practices to Detect Neural Fake News.** [[paper]](https://aclanthology.org/2022.coling-1.106.pdf) ![](https://img.shields.io/badge/COLING%202022-orange) ![](https://img.shields.io/badge/2022.10-blue)\n\n  *Artidoro Pagnoni, Martin Graciarena and Yulia Tsvetkov.*\n  \u003e Provide an assessment of the current landscape of generated text detection and identify three primary threat scenarios. Establish the minimax strategies that minimize the worst case scenario for the detector.\n\n- **Demystifying Neural Fake News via Linguistic Feature-Based Interpretation.** [[paper]](https://aclanthology.org/2022.coling-1.573.pdf) ![](https://img.shields.io/badge/COLING%202022-orange) ![](https://img.shields.io/badge/2022.10-blue)\n\n  *Ankit Aich, Souvik Bhattacharya and Natalie Parde.*\n  \u003e Conduct a linguistically interpretative examination of the feature vulnerabilities exploited by neural fake news generators. Establish 21 stylistic, complexity, and psychological features for detection.\n\n- **CoCo: Coherence-Enhanced Machine-Generated Text Detection Under Data Limitation With Contrastive Learning.** [[paper]](https://arxiv.org/pdf/2212.10341) ![](https://img.shields.io/badge/EMNLP%202023-orange) ![](https://img.shields.io/badge/2022.12-blue)\n\n  *Xiaoming Liu, Zhaohan Zhang, Yichen Wang, Yu Lan and Chao Shen.*\n  \u003e Present a coherence-based contrastive learning model named CoCo to detect the possible machine-generated text under low-resource scenario.\n\n- **How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection.** [[paper]](https://arxiv.org/pdf/2301.07597) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2023.01-blue)\n\n  *Biyang Guo, Xin Zhang, Ziyuan Wang, Minqi Jiang, Jinran Nie, Yuxuan Ding, Jianwei Yue and Yupeng Wu.*\n  \u003e Collect dataset the Human ChatGPT Comparison Corpus (HC3) and build three different detection systems to detect whether a certain text is generated by ChatGPT or humans.\n\n- **DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature.** [[paper]](https://arxiv.org/pdf/2301.11305) ![](https://img.shields.io/badge/ICML%202023-orange) ![](https://img.shields.io/badge/2023.01-blue)\n\n  *Eric Mitchell, Yoonho Lee, Alexander Khazatsky, Christopher D. Manning and Chelsea Finn.*\n  \u003e Propose DetectGPT, a zero-shot method for automated machine-generated text detection. To test if a passage came from a source model, DetectGPT compares the log probability of a candidate passage with the average log probability of several perturbations of the passage.\n\n- **ChatGPT or Human? Detect and Explain. Explaining Decisions of Machine Learning Model for Detecting Short ChatGPT-generated Text.** [[paper]](https://arxiv.org/pdf/2301.13852) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2023.01-blue)\n\n  *Sandra Mitrović, Davide Andreoletti and Omran Ayoub.*\n  \u003e Build Transformer-based model to discriminate between human-written and seemingly human text, focusing on short texts. Give some insights about ChatGPT writing style by SHAP explanations of the predictions.\n\n- **AI vs. Human -- Differentiation Analysis of Scientific Content Generation.** [[paper]](https://arxiv.org/pdf/2301.10416) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2023.01-blue)\n\n  *Yongqiang Ma, Jiawei Liu, Fan Yi, Qikai Cheng, Yong Huang, Wei Lu and Xiaozhong Liu.*\n  \u003e Investigate the detection methods from three perspectives: (1) feature-based detection method; (2) fine-tuned pre-trained detection model; (3) explainability of detection model. Further investigate the gap between AI-generated text and human-written text.\n\n- **ChatGPT Generated Text Detection.** [[paper]](https://www.researchgate.net/profile/Ercan-Canhasi/publication/366898047_ChatGPT_Generated_Text_Detection/links/63b76718097c7832ca932473/ChatGPT-Generated-Text-Detection.pdf) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2023.01-blue)\n\n  *Rexhep Shijaku and Ercan Canhasi.*\n  \u003e Present a classification model based on XGBoost for automatically detecting essays generated by ChatGPT.\n\n- **Linguistic Markers of AI-Generated Text Versus Human-Generated Text: Evidence from Hotel Reviews and News Headlines.** [[paper]](https://psyarxiv.com/mnyz8/download) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2023.01-blue)\n\n  *David M. Markowitz, Jeffrey Hancock and Jeremy Bailenson.*\n  \u003e Use ChatGPT to compare how it wrote hotel reviews and news headlines to human-generated counterparts across content, style, and structural features.\n\n- **Mutation-Based Adversarial Attacks on Neural Text Detectors.** [[paper]](https://arxiv.org/pdf/2302.05794) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2023.02-blue)\n\n  *Gongbo Liang, Jesus Guerrero and Izzat Alsmadi.*\n  \u003e Propose character- and word-based mutation operators for generating adversarial samples to attack state-of-the-art natural text detectors.\n\n- **GAN-Based Unsupervised Learning Approach to Generate and Detect Fake News.** [[paper]](https://link.springer.com/chapter/10.1007/978-3-031-22018-0_37) ![](https://img.shields.io/badge/ICSPN%202022-orange) ![](https://img.shields.io/badge/2023.02-blue)\n\n  *Pranjal Bhardwaj, Krishna Yadav, Hind Alsharif and Rania Anwar Aboalela.*\n  \u003e Develop an unsupervised-based approach to generate fake news using autoencoder and GAN. Further describe the use of discriminators in detecting machine-generated fake news.\n\n- **Combat AI With AI: Counteract Machine-Generated Fake Restaurant Reviews on Social Media.** [[paper]](https://arxiv.org/pdf/2302.07731.pdf) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2023.02-blue)\n\n  *Alessandro Gambetti and Qiwei Han.*\n  \u003e Propose to leverage the high-quality elite restaurant reviews verified by Yelp to generate fake reviews from the OpenAI GPT review creator and ultimately fine-tune a GPT output detector to predict fake reviews that significantly outperform existing solutions.\n\n- **Accurate Generated Text Detection Based on Deep Layer-wise Relevance Propagation.** [[paper]](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\u0026arnumber=10104941) ![](https://img.shields.io/badge/ICBDA%202023-orange) ![](https://img.shields.io/badge/2023.03-blue)\n\n  *Mengjie Guo, Limin Liu, Meicheng Guo, Siyuan Liu and Zhiwei Xu.*\n  \u003e Propose a deep interpretable model to achieve accurate detection of the generated texts. In detail, a feature extraction method based on Layer-wise Relevance Propagation is proposed to improve the feature mining performance for detection of generated texts.\n\n- **Stylometric Detection of AI-Generated Text in Twitter Timelines.** [[paper]](https://arxiv.org/pdf/2303.03697) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2023.03-blue)\n\n  *Tharindu Kumarage, Joshua Garland, Amrita Bhattacharjee, Kirill Trapeznikov, Scott Ruston and Huan Liu.*\n  \u003e Propose two simple architectures to utilize three categories of stylometric features towards 1) discriminating between human-written and AI-generated tweets and 2) detecting if and when an AI starts to generate tweets in a given Twitter timeline.\n\n- **ChatGPT or academic scientist? Distinguishing authorship with over 99% accuracy using off-the-shelf machine learning tools.** [[paper]](https://arxiv.org/pdf/2303.16352) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2023.03-blue)\n\n  *Heather Desaire, Aleesa E. Chua, Madeline Isom, Romana Jarosova and David Hua.*\n  \u003e With a set of 20 features, build a model that assigned the author, as human or AI, at well over 99% accuracy, resulting in 20 times fewer misclassified documents compared to the field-leading approach.\n\n- **Detection of AI-generated Essays in Writing Assessments.** [[paper]](https://www.psychologie-aktuell.com/fileadmin/Redaktion/Journale/ptam_2023-1/PTAM__1-2023_5_kor.pdf) ![](https://img.shields.io/badge/Psychological%20Testing%20and%20Assessment%20Modeling%202023-orange) ![](https://img.shields.io/badge/2023.03-blue)\n\n  *Duanli Yan, Michael Fauss, Jiangang Hao, Wenju Cui.*\n  \u003e Show how AI-generated essays are similar or different from human-written essays based on a set of typical prompts for a sample from a large-scale assessment. Introduce two classifiers that can detect AI-generated essays with a high accuracy of over 95%.\n\n- **Comparing Abstractive Summaries Generated by ChatGPT to Real Summaries Through Blinded Reviewers and Text Classification Algorithms.** [[paper]](https://arxiv.org/pdf/2303.17650) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2023.03-blue)\n\n  *Mayank Soni, Vincent Wade.*\n  \u003e Evaluate the performance of ChatGPT on Abstractive Summarization by the means of automated metrics and blinded human reviewers. Also build automatic text classifiers to detect ChatGPT generated summaries. Find that while text classification algorithms can distinguish between real and generated summaries, humans are unable to distinguish between real summaries and those produced by ChatGPT.\n\n- **Distinguishing ChatGPT(-3.5, -4)-generated and human-written papers through Japanese stylometric analysis.** [[paper]](https://arxiv.org/pdf/2304.05534) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2023.04-blue)\n\n  *Wataru Zaitsu and Mingzhe Jin.*\n  \u003e Perform multi-dimensional scaling (MDS) to confirm the distributions of 216 texts of three classes (human, GPT-3.5, GPT-4) focusing on the following stylometric features: (1) bigrams of parts-of-speech, (2) bigram of postpositional particle words, (3) positioning of commas, and (4) rate of function words.\n\n- **Evaluating AIGC Detectors on Code Content.** [[paper]](https://arxiv.org/pdf/2304.05193) ![](https://img.shields.io/badge/Preprint-orange) ![](https://img.shields.io/badge/2023.04-blue)\n\n  *Jian Wang, Shangqing Liu, Xiaofei Xie and Yi Li.*\n  \u003e Present the first empirical study on evaluating existing AIGC detectors in the software domain. Create a comprehensive dataset including 492.5K samples comprising code-related content produced by ChatGPT and evaluate six AIGC detectors on this dataset.\n\n- **Detection of Fake Generated Scientific Abstracts.** [[paper]](https://arxiv.org/pdf/2304.06148) ![](https://img.shields.io/","projects_url":"https://awesome.ecosyste.ms/api/v1/lists/ictmcg%2Fawesome-machine-generated-text/projects"}