Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.
Awesome Lists | Featured Topics | Projects
https://github.com/WangRongsheng/Awesome-LLM-with-RAG

A curated list of Large Language Model with RAG
https://github.com/WangRongsheng/Awesome-LLM-with-RAG
List: Awesome-LLM-with-RAG
Last synced: 19 days ago
JSON representation
A curated list of Large Language Model with RAG
Host: GitHub
URL: https://github.com/WangRongsheng/Awesome-LLM-with-RAG
Owner: WangRongsheng
Created: 2023-10-25T11:37:37.000Z (over 1 year ago)
Default Branch: main
Last Pushed: 2023-11-03T13:17:41.000Z (over 1 year ago)
Last Synced: 2025-01-27T00:01:49.091Z (26 days ago)
Language: Python
Homepage:
Size: 3.8 MB
Stars: 77
Watchers: 2
Forks: 6
Open Issues: 0
Metadata Files:
- Readme: README.md
Awesome Lists containing this project

ultimate-awesome - Awesome-LLM-with-RAG - A curated list of Large Language Model with RAG. (Other Lists / Julia Lists)
README

        # Awesome-LLM-with-RAG

Enhancing Large Language Models with Retrieval Augmented Generation.

![](./assets/rag.png)

# Paper

- Unlimiformer: Long-Range Transformers with Unlimited Length Input. [*2023.10.30*] [[Arxiv](https://arxiv.org/abs/2305.01625)] 

- Active Retrieval Augmented Generation. [*2023.10.22*] [[Arxiv](https://arxiv.org/abs/2305.06983)]

- Understanding Retrieval Augmentation for Long-Form Question Answering. [*2023.10.18*] [[Arxiv](https://arxiv.org/abs/2310.12150)]

- Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection. [*2023.10.17*][[Arxiv](https://arxiv.org/abs/2310.11511)][[Code](https://github.com/AkariAsai/self-rag)]

- RaLLe: A Framework for Developing and Evaluating Retrieval-Augmented Large Language Models. [*2023.10.16*] [[Arxiv](https://arxiv.org/abs/2308.10633)]

- RegaVAE: A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modeling. [*2023.10.16*] [[Arxiv](https://arxiv.org/abs/2310.10567)]

- Chameleon: a Heterogeneous and Disaggregated Accelerator System for Retrieval-Augmented Language Models. [*2023.10.15*] [[Arxiv](https://arxiv.org/abs/2310.09949)]

- FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation. [*2023.10.11*] [[Arxiv](https://arxiv.org/abs/2305.14251)]     

- InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining. [*2023.10.11*] [[Arxiv](https://arxiv.org/abs/2310.07713)]

- Goodtriever: Adaptive Toxicity Mitigation with Retrieval-augmented Models. [*2023.10.11*] [[Arxiv](https://arxiv.org/abs/2310.07589)]

- Retrieve Anything To Augment Large Language Models. [*2023.10.11*] [[Arxiv](https://arxiv.org/abs/2310.07554)]

- VerifAI: Verified Generative AI. [*2023.10.11*][[Arxiv](https://arxiv.org/abs/2307.02796)]

- Crossing the Threshold: Idiomatic Machine Translation through Retrieval Augmentation and Loss Weighting. [*2023.10.10*] [[Arxiv](https://arxiv.org/abs/2310.07081)]

- RAUCG: Retrieval-Augmented Unsupervised Counter Narrative Generation for Hate Speech. [*2023.10.09*] [[Arxiv](https://arxiv.org/abs/2310.05650)]

- GROVE: A Retrieval-augmented Complex Story Generation Framework with A Forest of Evidence. [*2023.10.08*] [[Arxiv](https://arxiv.org/abs/2310.05388)]

- Augmented Embeddings for Custom Retrievals. [*2023.10.08*] [[Arxiv](https://arxiv.org/abs/2310.05380)]

- Retrieval-Generation Synergy Augmented Large Language Models. [*2023.10.08*] [[Arxiv](https://arxiv.org/abs/2310.05149)]

- Self-Knowledge Guided Retrieval Augmentation for Large Language Models. [*2023.10.08*] [[Arxiv](https://arxiv.org/abs/2310.05002)]

- RA-DIT: Retrieval-Augmented Dual Instruction Tuning. [*2023.10.08*] [[Arxiv](https://arxiv.org/abs/2310.01352)]

- Retrieving Multimodal Information for Augmented Generation: A Survey. [*2023.10.07*] [[Arxiv](https://arxiv.org/abs/2303.10868)]

- RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation. [*2023.10.06*] [[Arxiv](https://arxiv.org/abs/2310.04408)]

- Keyword Augmented Retrieval: Novel framework for Information Retrieval integrated with speech interface. [*2023.10.06*] [[Arxiv](https://arxiv.org/abs/2310.04205)]

- Enhancing Financial Sentiment Analysis via Retrieval Augmented Large Language Models. [*2023.10.06*] [[Arxiv](https://arxiv.org/abs/2310.04027)]

- Retrieval-augmented Generation to Improve Math Question-Answering: Trade-offs Between Groundedness and Human Preference. [*2023.10.04*] [[Arxiv](https://arxiv.org/abs/2310.03184)]

- Making Retrieval-Augmented Language Models Robust to Irrelevant Context. [*2023.10.02*] [[Arxiv](https://arxiv.org/abs/2310.01558)]

- BTR: Binary Token Representations for Efficient Retrieval Augmented Language Models. [*2023.10.02*] [[Arxiv](https://arxiv.org/abs/2310.01329)]

- Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering. [*2023.09.29*] [[Arxiv](https://arxiv.org/abs/2309.17133)]

- Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models. [*2023.09.29*] [[Arxiv](https://arxiv.org/abs/2309.17050)]

- RAGAS: Automated Evaluation of Retrieval Augmented Generation. [*2023.09.26*] [[Arxiv](https://arxiv.org/abs/2309.15217)]

- Furthest Reasoning with Plan Assessment: Stable Reasoning Path with Retrieval-Augmented Large Language Models. [*2023.09.22*] [[Arxiv](https://arxiv.org/abs/2309.12767)]

- RUEL: Retrieval-Augmented User Representation with Edge Browser Logs for Sequential Recommendation. [*2023.09.19*] [[Arxiv](https://arxiv.org/abs/2309.10469)]

- Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning. [*2023.09.19*] [[Arxiv](https://arxiv.org/abs/2205.14704)]

- Revisiting and Improving Retrieval-Augmented Deep Assertion Generation. [*2023.09.18*] [[Arxiv](https://arxiv.org/abs/2309.10264)]

- RECAP: Retrieval-Augmented Audio Captioning. [*2023.09.18*] [[Arxiv](https://arxiv.org/abs/2309.09836)]

- Differentiable Retrieval Augmentation via Generative Language Modeling for E-commerce Query Intent Classification. [*2023.09.15*] [[Arxiv](https://arxiv.org/abs/2308.09308)]

- Retrieval-Augmented Text-to-Audio Generation. [*2023.09.14*] [[Arxiv](https://arxiv.org/abs/2309.08051)]

- RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair. [*2023.09.12*] [[Arxiv](https://arxiv.org/abs/2309.06057)]

- Retrieval-Augmented Meta Learning for Low-Resource Text Classification. [*2023.09.10*] [[Arxiv](https://arxiv.org/abs/2309.04979)]

- RAHNet: Retrieval Augmented Hybrid Network for Long-tailed Graph Classification. [*2023.09.07*] [[Arxiv](https://arxiv.org/abs/2308.02335)]

- Benchmarking Large Language Models in Retrieval-Augmented Generation. [*2023.09.04*] [[Arxiv](https://arxiv.org/abs/2309.01431)]

- Retrieval-augmented GPT-3.5-based Text-to-SQL Framework with Sample-aware Prompting and Dynamic Revision Chain. [*2023.09.04*] [[Arxiv](https://arxiv.org/abs/2307.05074)]

- RAMP: Retrieval-Augmented MOS Prediction via Confidence-based Dynamic Weighting. [*2023.08.31*] [[Arxiv](https://arxiv.org/abs/2308.16488)]

- Vector Search with OpenAI Embeddings: Lucene Is All You Need. [*2023.08.29*] [[Arxiv](https://arxiv.org/abs/2308.14963)]

- Soft Prompt Tuning for Augmenting Dense Retrieval with Large Language Models. [*2023.08.29*] [[Arxiv](https://arxiv.org/abs/2307.08303)]

- RSpell: Retrieval-augmented Framework for Domain Adaptive Chinese Spelling Check. [*2023.08.16*] [[Arxiv](https://arxiv.org/abs/2308.08176)]

- Enhancing Performance on Seen and Unseen Dialogue Scenarios using Retrieval-Augmented End-to-End Task-Oriented System. [*2023.08.16*] [[Arxiv](https://arxiv.org/abs/2308.08169)]

- RAVEN: In-Context Learning with Retrieval Augmented Encoder-Decoder Language Models. [*2023.08.15*] [[Arxiv](https://arxiv.org/abs/2308.07922)]

- Diffusion Based Augmentation for Captioning and Retrieval in Cultural Heritage. [*2023.08.14*] [[Arxiv](https://arxiv.org/abs/2308.07151)]

- Encode-Store-Retrieve: Enhancing Memory Augmentation through Language-Encoded Egocentric Perception. [*2023.08.10*] [[Arxiv](https://arxiv.org/abs/2308.05822)]

- Hybrid Retrieval-Augmented Generation for Real-time Composition Assistance. [*2023.08.08*] [[Arxiv](https://arxiv.org/abs/2308.04215)]

- Retrieval-based Knowledge Augmented Vision Language Pre-training. [*2023.08.06*] [[Arxiv](https://arxiv.org/abs/2304.13923)]

- Retrieval Augmented Generation and Representative Vector Summarization for large unstructured textual data in Medical Education. [*2023.08.01*] [[Arxiv](https://arxiv.org/abs/2308.00479)]

- In-Context Retrieval-Augmented Language Models. [*2023.08.01*] [[Arxiv](https://arxiv.org/abs/2302.00083)]

- Select and Augment: Enhanced Dense Retrieval Knowledge Graph Augmentation. [*2023.07.28*] [[Arxiv](https://arxiv.org/abs/2307.15776)]

- Exploring Annotation-free Image Captioning with Retrieval-augmented Pseudo Sentence Generation. [*2023.07.28*] [[Arxiv](https://arxiv.org/abs/2307.14750)]

- RRAML: Reinforced Retrieval Augmented Machine Learning. [*2023.07.27*] [[Arxiv](https://arxiv.org/abs/2307.12798)]

- VITR: Augmenting Vision Transformers with Relation-Focused Learning for Cross-Modal Information Retrieval. [*2023.07.27*] [[Arxiv](https://arxiv.org/abs/2302.06350)]

- TabR: Unlocking the Power of Retrieval-Augmented Tabular Deep Learning. [*2023.07.26*] [[Arxiv](https://arxiv.org/abs/2307.14338)]

- Prompt Generate Train (PGT): Few-shot Domain Adaption of Retrieval Augmented Generation Models for Open Book Question-Answering. [*2023.07.25*] [[Arxiv](https://arxiv.org/abs/2307.05915)]

- Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation. [*2023.07.23*] [[Arxiv](https://arxiv.org/abs/2307.11019)]

- Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation. [*2023.07.13*] [[Arxiv](https://arxiv.org/abs/2307.06940)]

- Cross-Lingual Retrieval Augmented Prompt for Low-Resource Languages. [*2023.07.10*] [[Arxiv](https://arxiv.org/abs/2212.09651)]

- TRAC: Trustworthy Retrieval Augmented Chatbot. [*2023.07.06*] [[Arxiv](https://arxiv.org/abs/2307.04642)]

- Improving Retrieval-Augmented Large Language Models via Data Importance Learning. [*2023.07.06*] [[Arxiv](https://arxiv.org/abs/2307.03027)]

- Surface-Based Retrieval Reduces Perplexity of Retrieval-Augmented Language Models. [*2023.07.04*] [[Arxiv](https://arxiv.org/abs/2305.16243)]

- Diverse Retrieval-Augmented In-Context Learning for Dialogue State Tracking. [*2023.07.03*] [[Arxiv](https://arxiv.org/abs/2307.01453)]

- When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories. [*2023.07.02*][[Arxiv](https://arxiv.org/abs/2212.10511)]

- LeanDojo: Theorem Proving with Retrieval-Augmented Language Models. [*2023.06.27*] [[Arxiv](https://arxiv.org/abs/2306.15626)]

- SAIL: Search-Augmented Instruction Learning. [*2023.06.25*][[Arxiv](https://arxiv.org/abs/2305.15225)]

- Long-range Language Modeling with Self-retrieval. [*2023.06.23*] [[Arxiv](https://arxiv.org/abs/2306.13421)]

- Retrieval-Based Transformer for Table Augmentation. [*2023.06.20*] [[Arxiv](https://arxiv.org/abs/2306.11843)]

- Weakly-Supervised Scientific Document Classification via Retrieval-Augmented Multi-Stage Training. [*2023.06.12*] [[Arxiv](https://arxiv.org/abs/2306.07193)]

- Speech-to-Text Adapter and Speech-to-Entity Retriever Augmented LLMs for Speech Understanding. [*2023.06.08*] [[Arxiv](https://arxiv.org/abs/2306.07944)]

- RETA-LLM: A Retrieval-Augmented Large Language Model Toolkit. [*2023.06.08*] [[Arxiv](https://arxiv.org/abs/2306.05212)]

- Large language models can be easily distracted by irrelevant context. [*2023.06.06*][[Arxiv](https://arxiv.org/abs/2302.00093)]

- Retrieval-Augmented Multimodal Language Modeling. [*2023.06.05*] [[Arxiv](https://arxiv.org/abs/2211.12561)]

- Pre-computed memory or on-the-fly encoding? A hybrid approach to retrieval augmentation makes the most of your compute. [*2023.06.02*] [[Arxiv](https://arxiv.org/abs/2301.10448)]

- Reimagining Retrieval Augmented Language Models for Answering Queries. [*2023.06.01*] [[Arxiv](https://arxiv.org/abs/2306.01061)]

- Almanac: Retrieval-Augmented Language Models for Clinical Medicine. [*2023.05.31*] [[Arxiv](https://arxiv.org/abs/2303.01229)]

- LMCap: Few-shot Multilingual Image Captioning by Retrieval Augmented Language Model Prompting. [*2023.05.31*] [[Arxiv](https://arxiv.org/abs/2305.19821)]

- Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels. [*2023.05.30*] [[Arxiv](https://arxiv.org/abs/2305.19518)]

- Improving accuracy of GPT-3/4 results on biomedical data using a retrieval-augmented language model. [*2023.05.30*] [[Arxiv](https://arxiv.org/abs/2305.17116)]

- Prompt-Guided Retrieval Augmentation for Non-Knowledge-Intensive Tasks. [*2023.05.28*] [[Arxiv](https://arxiv.org/abs/2305.17653)]

- Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-In. [*2023.05.26*] [[Arxiv](https://arxiv.org/abs/2305.17331)]

- Nonparametric Masked Language Modeling. [*2023.05.25*] [[Arxiv](https://arxiv.org/abs/2212.01349)]  

- KNN-LM Does Not Improve Open-ended Text Generation. [*2023.05.24*] [[Arxiv](https://arxiv.org/abs/2305.14625)]  

- Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy. [*2023.05.24*] [[Arxiv](https://arxiv.org/abs/2305.15294)]

- Referral Augmentation for Zero-Shot Information Retrieval. [*2023.05.24*] [[Arxiv](https://arxiv.org/abs/2305.15098)]

- Enabling Large Language Models to Generate Text with Citations. [*2023.05.24*][[Arxiv](https://arxiv.org/abs/2305.14627)]

- REPLUG: Retrieval-Augmented Black-Box Language Models. [*2023.05.24*] [[Arxiv](https://arxiv.org/abs/2301.12652)]

- Query Rewriting for Retrieval-Augmented Large Language Models. [*2023.05.23*] [[Arxiv](https://arxiv.org/abs/2305.14283)]

- Retrieval-augmented Multi-label Text Classification. [*2023.05.22*] [[Arxiv](https://arxiv.org/abs/2305.13058)]

- MALM: Mask Augmentation based Local Matching for Food-Recipe Retrieval. [*2023.05.18*] [[Arxiv](https://arxiv.org/abs/2305.11327)]

- Tram: A Token-level Retrieval-augmented Mechanism for Source Code Summarization. [*2023.05.18*] [[Arxiv](https://arxiv.org/abs/2305.11074)]

- Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory. [*2023.05.17*] [[Arxiv](https://arxiv.org/abs/2305.02437)]

- DAMO-NLP at SemEval-2023 Task 2: A Unified Retrieval-augmented System for Multilingual Named Entity Recognition. [*2023.05.16*] [[Arxiv](https://arxiv.org/abs/2305.03688)]

- Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model. [*2023.05.06*] [[Arxiv](https://arxiv.org/abs/2212.09146)]

- Augmenting Passage Representations with Query Generation for Enhanced Cross-Lingual Dense Retrieval. [*2023.05.06*] [[Arxiv](https://arxiv.org/abs/2305.03950)]

- Retrieval Augmented Chest X-Ray Report Generation using OpenAI GPT models. [*2023.05.05*] [[Arxiv](https://arxiv.org/abs/2305.03660)]

- Discern and Answer: Mitigating the Impact of Misinformation in Retrieval-Augmented Models with Discriminators. [*2023.05.02*] [[Arxiv](https://arxiv.org/abs/2305.01579)]

- Retrieval Enhanced Data Augmentation for Question Answering on Privacy Policies. [*2023.04.22*] [[Arxiv](https://arxiv.org/abs/2204.08952)]

- A data augmentation perspective on diffusion models and retrieval. [*2023.04.20*] [[Arxiv](https://arxiv.org/abs/2304.10253)]

- Retrieval-Augmented Classification with Decoupled Representation. [*2023.04.11*] [[Arxiv](https://arxiv.org/abs/2303.13065)]

- LADER: Log-Augmented DEnse Retrieval for Biomedical Literature Search. [*2023.04.10*] [[Arxiv](https://arxiv.org/abs/2304.04590)]

- ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model. [*2023.04.03*] [[Arxiv](https://arxiv.org/abs/2304.01116)]

- REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory. [*2023.04.03*] [[Arxiv](https://arxiv.org/abs/2212.05221)]

- SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation. [*2023.03.28*] [[Arxiv](https://arxiv.org/abs/2209.15323)]

- On the Calibration and Uncertainty with Pólya-Gamma Augmentation for Dialog Retrieval Models. [*2023.03.15*] [[Arxiv](https://arxiv.org/abs/2303.08606)]

- Suffix Retrieval-Augmented Language Modeling. [*2023.03.14*] [[Arxiv](https://arxiv.org/abs/2211.03053)]

- Semantic-Preserving Augmentation for Robust Image-Text Retrieval. [*2023.03.09*] [[Arxiv](https://arxiv.org/abs/2303.05692)]

- AugTriever: Unsupervised Dense Retrieval by Scalable Data Augmentation. [*2023.03.07*] [[Arxiv](https://arxiv.org/abs/2212.08841)]

- RAMM: Retrieval-augmented Biomedical Visual Question Answering with Multi-modal Pre-training. [*2023.03.01*] [[Arxiv](https://arxiv.org/abs/2303.00534)]

- Retrieved Sequence Augmentation for Protein Representation Learning. [*2023.02.24*] [[Arxiv](https://arxiv.org/abs/2302.12563)]

- X-TRA: Improving Chest X-ray Tasks with Cross-Modal Retrieval Augmentation. [*2023.02.22*] [[Arxiv](https://arxiv.org/abs/2302.11352)]

- DocPrompting: Generating Code by Retrieving the Docs. [*2023.02.18*] [[Arxiv](https://arxiv.org/abs/2207.05987)]

- Retrieval-augmented Image Captioning. [*2023.02.16*] [[Arxiv](https://arxiv.org/abs/2302.08268)]

- How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval. [*2023.02.14*] [[Arxiv](https://arxiv.org/abs/2302.07452)]

- Characterizing Attribution and Fluency Tradeoffs for Retrieval-Augmented Large Language Models. [*2023.02.14*] [[Arxiv](https://arxiv.org/abs/2302.05578)]

- Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models. [*2023.02.10*] [[Arxiv](https://arxiv.org/abs/2212.08037)]

- Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning. [*2023.02.09*] [[Arxiv](https://arxiv.org/abs/2302.04858)]

- Augmenting Zero-Shot Dense Retrievers with Plug-in Mixture-of-Memories. [*2023.02.07*] [[Arxiv](https://arxiv.org/abs/2302.03754)]

- Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP. [*2023.01.23*] [[Arxiv](https://arxiv.org/abs/2212.14024)]      

- Learning Customized Visual Models with Retrieval-Augmented Knowledge. [*2023.01.17*] [[Arxiv](https://arxiv.org/abs/2301.07094)]

  

- Generation-Augmented Query Expansion For Code Retrieval. [*2022.12.20*] [[Arxiv](https://arxiv.org/abs/2212.10692)]

- Augmenting Scientific Creativity with Retrieval across Knowledge Domains. [*2022.12.14*] [[Arxiv](https://arxiv.org/abs/2206.01328)]

- Training Language Models with Memory Augmentation. [*2022.11.29*] [[Arxiv](https://arxiv.org/abs/2205.12674)]

- Re-Imagen: Retrieval-Augmented Text-to-Image Generator. [*2022.11.21*] [[Arxiv](https://arxiv.org/abs/2209.14491)]

- Atlas: Few-shot Learning with Retrieval Augmented Language Models. [*2022.11.16*] [[Arxiv](https://arxiv.org/abs/2208.03299)]

- Retrieval-Augmented Generative Question Answering for Event Argument Extraction. [*2022.11.13*] [[Arxiv](https://arxiv.org/abs/2211.07067)]

- kNN-Prompt: Nearest Neighbor Zero-Shot Inference. [*2022.11.01*] [[Arxiv](https://arxiv.org/abs/2205.13792)]

- Improving Natural-Language-based Audio Retrieval with Transfer Learning and Audio & Text Augmentations. [*2022.10.29*] [[Arxiv](https://arxiv.org/abs/2208.11460)]

- Retrieval Augmented Visual Question Answering with Outside Knowledge. [*2022.10.29*] [[Arxiv](https://arxiv.org/abs/2210.03809)]

- You can't pick your neighbors, or can you? When and how to rely on retrieval in the kNN-LM. [*2022.10.28*] [[Arxiv](https://arxiv.org/abs/2210.15859)] 

- QUILL: Query Intent with Large Language Models using Retrieval Augmentation and Multi-stage Distillation. [*2022.10.27*] [[Arxiv](https://arxiv.org/abs/2210.15718)]

- XRICL: Cross-lingual Retrieval-Augmented In-Context Learning for Cross-lingual Text-to-SQL Semantic Parsing. [*2022.10.24*] [[Arxiv](https://arxiv.org/abs/2210.13693)]

- Retrieval Augmentation for Commonsense Reasoning: A Unified Approach. [*2022.10.23*] [[Arxiv](https://arxiv.org/abs/2210.12887)]

- RACE: Retrieval-Augmented Commit Message Generation. [*2022.10.22*] [[Arxiv](https://arxiv.org/abs/2203.02700)]

- MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text. [*2022.10.20*] [[Arxiv](https://arxiv.org/abs/2210.02928)]

- Unsupervised Cross-Task Generalization via Retrieval Augmentation. [*2022.10.17*] [[Arxiv](https://arxiv.org/abs/2204.07937)]

- Category-Level Pose Retrieval with Contrastive Features Learnt with Occlusion Augmentation. [*2022.10.12*] [[Arxiv](https://arxiv.org/abs/2208.06195)]

- Retrieval Augmentation for T5 Re-ranker using External Sources. [*2022.10.11*] [[Arxiv](https://arxiv.org/abs/2210.05145)]

- Improving Robustness of Retrieval Augmented Translation via Shuffling of Suggestions. [*2022.10.10*] [[Arxiv](https://arxiv.org/abs/2210.05059)]

- Improving Retrieval Augmented Neural Machine Translation by Controlling Source and Fuzzy-Match Interactions. [*2022.10.10*] [[Arxiv](https://arxiv.org/abs/2210.05047)]

- Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering. [*2022.10.05*] [[Arxiv](https://arxiv.org/abs/2210.02627)]

- FiD-Light: Efficient and Effective Retrieval-Augmented Text Generation. [*2022.09.28*] [[Arxiv](https://arxiv.org/abs/2209.14290)]

- SCL-RAI: Span-based Contrastive Learning with Retrieval Augmented Inference for Unlabeled Entity Problem in NER. [*2022.09.24*] [[Arxiv](https://arxiv.org/abs/2209.01646)]

- Segment Augmentation and Differentiable Ranking for Logo Retrieval. [*2022.09.13*] [[Arxiv](https://arxiv.org/abs/2209.02482)]

- MQRetNN: Multi-Horizon Time Series Forecasting with Retrieval Augmentation. [*2022.09.08*] [[Arxiv](https://arxiv.org/abs/2207.10517)]

- Unsupervised Dense Information Retrieval with Contrastive Learning. [*2022.08.29*] [[Arxiv](https://arxiv.org/abs/2112.09118)]  

- Retrieval-Augmented Transformer for Image Captioning. [*2022.08.22*] [[Arxiv](https://arxiv.org/abs/2207.13162)]

- A Feature-space Multimodal Data Augmentation Technique for Text-video Retrieval. [*2022.08.03*] [[Arxiv](https://arxiv.org/abs/2208.02080)]

- Paired Cross-Modal Data Augmentation for Fine-Grained Image-to-Text Retrieval. [*2022.07.28*] [[Arxiv](https://arxiv.org/abs/2207.14428)]

- Text-Guided Synthesis of Artistic Images with Retrieval-Augmented Diffusion Models. [*2022.07.26*] [[Arxiv](https://arxiv.org/abs/2207.13038)]

- Multi-Task Retrieval-Augmented Text Generation with Relevance Sampling. [*2022.07.06*] [[Arxiv](https://arxiv.org/abs/2207.03030)]

- Learning Test-time Augmentation for Content-based Image Retrieval. [*2022.07.05*] [[Arxiv](https://arxiv.org/abs/2002.01642)]

- BashExplainer: Retrieval-Augmented Bash Code Comment Generation based on Fine-tuned CodeBERT. [*2022.06.27*] [[Arxiv](https://arxiv.org/abs/2206.13325)]

- Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval. [*2022.06.09*] [[Arxiv](https://arxiv.org/abs/2201.12431)]

- Improving Contrastive Learning of Sentence Embeddings with Case-Augmented Positives and Retrieved Negatives. [*2022.06.06*] [[Arxiv](https://arxiv.org/abs/2206.02457)]

- Retrieval-Augmented Multilingual Keyphrase Generation with Retriever-Generator Iterative Training. [*2022.06.01*] [[Arxiv](https://arxiv.org/abs/2205.10471)]

- ZusammenQA: Data Augmentation with Specialized Models for Cross-lingual Open-retrieval Question Answering System. [*2022.05.30*] [[Arxiv](https://arxiv.org/abs/2205.14981)]

- Cache-Augmented Inbatch Importance Resampling for Training Recommender Retriever. [*2022.05.30*] [[Arxiv](https://arxiv.org/abs/2205.14859)]

- Retrieval-Augmented Reinforcement Learning. [*2022.05.24*] [[Arxiv](https://arxiv.org/abs/2202.08417)]

- Convex Augmentation for Total Variation Based Phase Retrieval. [*2022.04.21*] [[Arxiv](https://arxiv.org/abs/2205.00834)]

- Mention Memory: incorporating textual knowledge into Transformers through entity mention attention. [*2022.04.19*] [[Arxiv](https://arxiv.org/abs/2110.06176)] 

- End-to-End Table Question Answering via Retrieval-Augmented Generation. [*2022.03.30*] [[Arxiv](https://arxiv.org/abs/2203.16714)]

- Teaching language models to support answers with verified quotes. [*2022.03.21*] [[Arxiv](https://arxiv.org/abs/2203.11147)]

- Augmenting Document Representations for Dense Retrieval with Interpolation and Perturbation. [*2022.03.16*] [[Arxiv](https://arxiv.org/abs/2203.07735)]

- Memorizing Transformers. [*2022.03.16*] [[Arxiv](https://arxiv.org/abs/2203.08913)]

- ReACC: A Retrieval-Augmented Code Completion Framework. [*2022.03.15*] [[Arxiv](https://arxiv.org/abs/2203.07722)]

- Novelty Controlled Paraphrase Generation with Retrieval Augmented Conditional Prompt Tuning. [*2022.03.12*] [[Arxiv](https://arxiv.org/abs/2202.00535)]

- Controllable Semantic Parsing via Retrieval Augmentation. [*2022.02.23*] [[Arxiv](https://arxiv.org/abs/2110.08458)]

- Retrieval Augmented Classification for Long-Tail Visual Recognition. [*2022.02.22*] [[Arxiv](https://arxiv.org/abs/2202.11233)]

- A Survey on Retrieval-Augmented Text Generation. [*2022.02.13*] [[Arxiv](https://arxiv.org/abs/2202.01110)]

- InPars: Data Augmentation for Information Retrieval using Large Language Models. [*2022.02.10*] [[Arxiv](https://arxiv.org/abs/2202.05144)]

- Improving language models by retrieving from trillions of tokens. [*2022.02.07*] [[Arxiv](https://arxiv.org/abs/2112.04426)]

- Efficient Nearest Neighbor Language Models. [*2021.11.15*] [[Arxiv](https://arxiv.org/abs/2109.04212)]

- One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval. [*2021.10.28*] [[Arxiv](https://arxiv.org/abs/2107.11976)]   

- Noise-Augmented Privacy-Preserving Empirical Risk Minimization with Dual-purpose Regularizer and Privacy Budget Retrieval and Recycling. [*2021.10.16*] [[Arxiv](https://arxiv.org/abs/2110.08676)]

- RETRONLU: Retrieval Augmented Task-Oriented Semantic Parsing. [*2021.09.21*] [[Arxiv](https://arxiv.org/abs/2109.10410)]

- Robust Retrieval Augmented Generation for Zero-shot Slot Filling. [*2021.09.13*] [[Arxiv](https://arxiv.org/abs/2108.13934)]

- Retrieval Augmented Code Generation and Summarization. [*2021.09.10*] [[Arxiv](https://arxiv.org/abs/2108.11601)]

- Two-pronged Strategy: Lightweight Augmented Graph Network Hashing for Scalable Image Retrieval. [*2021.08.09*] [[Arxiv](https://arxiv.org/abs/2108.03914)]

- Generation-Augmented Retrieval for Open-domain Question Answering. [*2021.08.06*] [[Arxiv](https://arxiv.org/abs/2009.08553)]

- Retrieval-Augmented Transformer-XL for Close-Domain Dialog Generation. [*2021.05.19*] [[Arxiv](https://arxiv.org/abs/2105.09235)]

- Retrieval-Augmented Generation for Code Summarization via Hybrid GNN. [*2021.05.12*] [[Arxiv](https://arxiv.org/abs/2006.05405)]

- Retrieval Augmentation for Deep Neural Networks. [*2021.04.26*] [[Arxiv](https://arxiv.org/abs/2102.13030)]

- Cross-Modal Retrieval Augmentation for Multi-Modal Classification. [*2021.04.16*] [[Arxiv](https://arxiv.org/abs/2104.08108)]

- Retrieval Augmentation Reduces Hallucination in Conversation. [*2021.04.15*] [[Arxiv](https://arxiv.org/abs/2104.07567)]

- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. [*2021.04.12*] [[Arxiv](https://arxiv.org/abs/2005.11401)]

- Efficient Retrieval Augmented Generation from Unstructured Knowledge for Task-Oriented Dialog. [*2021.02.08*] [[Arxiv](https://arxiv.org/abs/2102.04643)]

- Memory Augmented Sequential Paragraph Retrieval for Multi-hop Question Answering. [*2021.02.07*] [[Arxiv](https://arxiv.org/abs/2102.03741)]

- Exemplar VAE: Linking Generative Models, Nearest Neighbor Retrieval, and Data Augmentation. [*2020.11.24*] [[Arxiv](https://arxiv.org/abs/2004.04795)]

- Entities as Experts: Sparse Memory Access with Entity Supervision. [*2020.10.06*] [[Arxiv](https://arxiv.org/abs/2004.07202)] 

- Augmenting Machine Learning with Information Retrieval to Recommend Real Cloned Code Methods for Code Completion. [*2020.10.02*] [[Arxiv](https://arxiv.org/abs/2010.00964)]

- Dense Passage Retrieval for Open-Domain Question Answering. [*2020.09.30*] [[Arxiv](https://arxiv.org/abs/2004.04906)] 

- Neural Retrieval for Question Answering with Cross-Attention Supervised Data Augmentation. [*2020.09.29*] [[Arxiv](https://arxiv.org/abs/2009.13815)]

- Retrieve Synonymous keywords for Frequent Queries in Sponsored Search in a Data Augmentation Way. [*2020.08.05*] [[Arxiv](https://arxiv.org/abs/2008.01969)]

- Tree-Augmented Cross-Modal Encoding for Complex-Query Video Retrieval. [*2020.07.05*] [[Arxiv](https://arxiv.org/abs/2007.02503)]

- On-The-Fly Information Retrieval Augmentation for Language Models. [*2020.07.03*] [[Arxiv](https://arxiv.org/abs/2007.01528)]

- Generalization through Memorization: Nearest Neighbor Language Models. [*2020.02.15*] [[Arxiv](https://arxiv.org/abs/1911.00172)]

- REALM: Retrieval-Augmented Language Model Pre-Training. [*2020.02.10*] [[Arxiv](https://arxiv.org/abs/2002.08909)]

- Web Table Extraction, Retrieval and Augmentation: A Survey. [*2020.02.05*] [[Arxiv](https://arxiv.org/abs/2002.00207)]

- Multi-Modal Music Information Retrieval: Augmenting Audio-Analysis with Visual Computing for Improved Music Video Analysis. [*2020.02.01*] [[Arxiv](https://arxiv.org/abs/2002.00251)]

- GRAPHENE: A Precise Biomedical Literature Retrieval Engine with Graph Augmented Deep Learning and External Knowledge Empowerment. [*2019.11.20*] [[Arxiv](https://arxiv.org/abs/1911.00760)]

- Discriminative Learning of Open-Vocabulary Object Retrieval and Localization by Negative Phrase Augmentation. [*2018.09.04*] [[Arxiv](https://arxiv.org/abs/1711.09509)]

- Neural Argument Generation Augmented with Externally Retrieved Evidence. [*2018.05.25*] [[Arxiv](https://arxiv.org/abs/1805.10254)]

- Gradient Augmented Information Retrieval with Autoencoders and Semantic Hashing. [*2018.03.12*] [[Arxiv](https://arxiv.org/abs/1803.04494)]

- Retrieval-Augmented Convolutional Neural Networks for Improved Robustness against Adversarial Examples. [*2018.02.26*] [[Arxiv](https://arxiv.org/abs/1802.09502)]

# _Paper

- Automatic Hallucination Assessment for Aligned Large Language Models via Transferable Adversarial Attacks. [*2023.10.19*] [[Arxiv](https://arxiv.org/abs/2310.12516)]

- Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection. [*2023.10.17*] [[Arxiv](https://arxiv.org/abs/2310.11511)]

- Towards reducing hallucination in extracting information from financial reports using Large Language Models. [*2023.10.16*] [[Arxiv](https://arxiv.org/abs/2310.10760)]

- In-Context Pretraining: Language Modeling Beyond Document Boundaries. [*2023.10.18*] [[Arxiv](https://arxiv.org/abs/2310.10638)]

- MechGPT, a language-based strategy for mechanics and materials modeling that connects knowledge across scales, disciplines and modalities. [*2023.10.16*] [[Arxiv](https://arxiv.org/abs/2310.10445)]

- CarExpert: Leveraging Large Language Models for In-Car Conversational Question Answering. [*2023.10.14*] [[Arxiv](https://arxiv.org/abs/2310.09536)]

- Towards Example-Based NMT with Multi-Levenshtein Transformers. [*2023.10.13*] [[Arxiv](https://arxiv.org/abs/2310.08967)]

- GenTKG: Generative Forecasting on Temporal Knowledge Graph. [*2023.10.11*] [[Arxiv](https://arxiv.org/abs/2310.07793)]

- Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity. [*2023.10.18*] [[Arxiv](https://arxiv.org/abs/2310.07521)]

- The Solution for the CVPR2023 NICE Image Captioning Challenge. [*2023.10.10*] [[Arxiv](https://arxiv.org/abs/2310.06879)]

- GPT-4 as an Agronomist Assistant? Answering Agriculture Exams Using Large Language Models. [*2023.10.12*] [[Arxiv](https://arxiv.org/abs/2310.06225)]

- Glitter or Gold? Deriving Structured Insights from Sustainability Reports via Large Language Models. [*2023.10.09*] [[Arxiv](https://arxiv.org/abs/2310.05628)]

- LLM4VV: Developing LLM-Driven Testsuite for Compiler Validation. [*2023.10.07*] [[Arxiv](https://arxiv.org/abs/2310.04963)]

- Retrieval meets Long Context Large Language Models. [*2023.10.04*] [[Arxiv](https://arxiv.org/abs/2310.03025)]

- Chatmap : Large Language Model Interaction with Cartographic Data. [*2023.09.28*] [[Arxiv](https://arxiv.org/abs/2310.01429)]

- Attention Sorting Combats Recency Bias In Long Context Language Models. [*2023.09.28*] [[Arxiv](https://arxiv.org/abs/2310.01427)]

- PDFTriage: Question Answering over Long, Structured Documents. [*2023.09.16*] [[Arxiv](https://arxiv.org/abs/2309.08872)]

- PACE-LM: Prompting and Augmentation for Calibrated Confidence Estimation with GPT-4 in Cloud Incident Root Cause Analysis. [*2023.09.29*] [[Arxiv](https://arxiv.org/abs/2309.05833)]

- Kani: A Lightweight and Highly Hackable Framework for Building Language Model Applications. [*2023.09.11*] [[Arxiv](https://arxiv.org/abs/2309.05542)]

- Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning. [*2023.09.05*] [[Arxiv](https://arxiv.org/abs/2309.02591)]

- A Study on the Implementation of Generative AI Services Using an Enterprise Data-Based LLM Application Architecture. [*2023.09.18*] [[Arxiv](https://arxiv.org/abs/2309.01105)]

- MEMORY-VQ: Compression for Tractable Internet-Scale Memory. [*2023.08.28*] [[Arxiv](https://arxiv.org/abs/2308.14903)]

- American Stories: A Large-Scale Structured Text Dataset of Historical U.S. Newspapers. [*2023.08.23*] [[Arxiv](https://arxiv.org/abs/2308.12477)]

- Domain Adaptive Code Completion via Language Models and Decoupled Domain Databases. [*2023.09.20*] [[Arxiv](https://arxiv.org/abs/2308.09313)]

- Answering Unseen Questions With Smaller Language Models Using Rationale Generation and Dense Retrieval. [*2023.10.12*] [[Arxiv](https://arxiv.org/abs/2308.04711)]

- Teaching Smaller Language Models To Generalise To Unseen Compositional Questions. [*2023.08.20*] [[Arxiv](https://arxiv.org/abs/2308.00946)]

- Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering. [*2023.07.31*] [[Arxiv](https://arxiv.org/abs/2307.16877)]

- Alleviating the Long-Tail Problem in Conversational Recommender Systems. [*2023.07.21*] [[Arxiv](https://arxiv.org/abs/2307.11650)]

- Meta-training with Demonstration Retrieval for Efficient Few-shot Learning. [*2023.06.30*] [[Arxiv](https://arxiv.org/abs/2307.00119)]

- RAPGen: An Approach for Fixing Code Inefficiencies in Zero-Shot. [*2023.06.29*] [[Arxiv](https://arxiv.org/abs/2306.17077)]

- Long-range Language Modeling with Self-retrieval. [*2023.06.23*] [[Arxiv](https://arxiv.org/abs/2306.13421)]

- Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories. [*2023.07.24*] [[Arxiv](https://arxiv.org/abs/2306.09224)]

- PoET: A generative model of protein families as sequences-of-sequences. [*2023.06.09*] [[Arxiv](https://arxiv.org/abs/2306.06156)]

- TimelineQA: A Benchmark for Question Answering over Timelines. [*2023.06.01*] [[Arxiv](https://arxiv.org/abs/2306.01069)]

- Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generation. [*2023.05.30*] [[Arxiv](https://arxiv.org/abs/2305.18846)]

- Multimodal Relation Extraction with Cross-Modal Retrieval and Synthesis. [*2023.05.25*] [[Arxiv](https://arxiv.org/abs/2305.16166)]

- Learning Answer Generation using Supervision from Automatic Question Answering Evaluators. [*2023.05.24*] [[Arxiv](https://arxiv.org/abs/2305.15344)]

- Adapting Language Models to Compress Contexts. [*2023.05.24*] [[Arxiv](https://arxiv.org/abs/2305.14788)]

- KNN-LM Does Not Improve Open-ended Text Generation. [*2023.05.23*] [[Arxiv](https://arxiv.org/abs/2305.14625)]

- FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation. [*2023.10.11*] [[Arxiv](https://arxiv.org/abs/2305.14251)]

- Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts. [*2023.10.02*] [[Arxiv](https://arxiv.org/abs/2305.13300)]

- Knowledge-Retrieval Task-Oriented Dialog Systems with Semi-Supervision. [*2023.05.22*] [[Arxiv](https://arxiv.org/abs/2305.13199)]

- The Web Can Be Your Oyster for Improving Large Language Models. [*2023.05.24*] [[Arxiv](https://arxiv.org/abs/2305.10998)]

- RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs. [*2023.07.11*] [[Arxiv](https://arxiv.org/abs/2305.08844)]

- Huatuo-26M, a Large-scale Chinese Medical QA Dataset. [*2023.05.02*] [[Arxiv](https://arxiv.org/abs/2305.01526)]

- LaMP: When Large Language Models Meet Personalization. [*2023.05.19*] [[Arxiv](https://arxiv.org/abs/2304.11406)]

- GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information. [*2023.05.16*] [[Arxiv](https://arxiv.org/abs/2304.09667)]

- BRENT: Bidirectional Retrieval Enhanced Norwegian Transformer. [*2023.04.19*] [[Arxiv](https://arxiv.org/abs/2304.09649)]

- Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study. [*2023.10.19*] [[Arxiv](https://arxiv.org/abs/2304.06762)]

- Improving Image Recognition by Retrieving from Web-Scale Image-Text Data. [*2023.04.11*] [[Arxiv](https://arxiv.org/abs/2304.05173)]

- RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation. [*2023.04.03*] [[Arxiv](https://arxiv.org/abs/2303.12570)]

- On the Generalization Ability of Retrieval-Enhanced Transformers. [*2023.02.23*] [[Arxiv](https://arxiv.org/abs/2302.12128)]

- $k$NN-Adapter: Efficient Domain Adaptation for Black-Box Language Models. [*2023.02.21*] [[Arxiv](https://arxiv.org/abs/2302.10879)]

- Why do Nearest Neighbor Language Models Work?. [*2023.01.17*] [[Arxiv](https://arxiv.org/abs/2301.02828)]

- You Truly Understand What I Need: Intellectual and Friendly Dialogue Agents grounding Knowledge and Persona. [*2023.01.06*] [[Arxiv](https://arxiv.org/abs/2301.02401)]

- Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP. [*2023.01.23*] [[Arxiv](https://arxiv.org/abs/2212.14024)]

- Parallel Context Windows for Large Language Models. [*2023.08.01*] [[Arxiv](https://arxiv.org/abs/2212.10947)]

- When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories. [*2023.07.02*] [[Arxiv](https://arxiv.org/abs/2212.10511)]

- Empowering Sentence Encoders with Prompting and Label Retrieval for Zero-shot Text Classification. [*2023.05.19*] [[Arxiv](https://arxiv.org/abs/2212.10391)]

- FiDO: Fusion-in-Decoder optimized for stronger performance and faster inference. [*2023.06.02*] [[Arxiv](https://arxiv.org/abs/2212.08153)]

- Neural Machine Translation with Contrastive Translation Memories. [*2022.12.06*] [[Arxiv](https://arxiv.org/abs/2212.03140)]

- ClueWeb22: 10 Billion Web Documents with Visual and Semantic Information. [*2022.12.01*] [[Arxiv](https://arxiv.org/abs/2211.15848)]

- Large Language Models Struggle to Learn Long-Tail Knowledge. [*2023.07.27*] [[Arxiv](https://arxiv.org/abs/2211.08411)]

- CELLS: A Parallel Corpus for Biomedical Lay Language Generation. [*2022.11.07*] [[Arxiv](https://arxiv.org/abs/2211.03818)]

- An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks. [*2022.10.30*] [[Arxiv](https://arxiv.org/abs/2210.16773)]

- Schema-aware Reference as Prompt Improves Data-Efficient Knowledge Graph Construction. [*2023.09.18*] [[Arxiv](https://arxiv.org/abs/2210.10709)]

- COFAR: Commonsense and Factual Reasoning in Image Search. [*2022.10.16*] [[Arxiv](https://arxiv.org/abs/2210.08554)]

- Variational Open-Domain Question Answering. [*2023.05.31*] [[Arxiv](https://arxiv.org/abs/2210.06345)]

- Decoupled Context Processing for Context Augmented Language Modeling. [*2022.10.11*] [[Arxiv](https://arxiv.org/abs/2210.05758)]

- CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation. [*2022.11.01*] [[Arxiv](https://arxiv.org/abs/2210.04873)]

- Recitation-Augmented Language Models. [*2023.02.16*] [[Arxiv](https://arxiv.org/abs/2210.01296)]

- Zemi: Learning Zero-Shot Semi-Parametric Language Models from Multiple Tasks. [*2023.05.22*] [[Arxiv](https://arxiv.org/abs/2210.00185)]

- Multimedia Generative Script Learning for Task Planning. [*2023.07.10*] [[Arxiv](https://arxiv.org/abs/2208.12306)]

- Can large language models reason about medical questions?. [*2023.01.24*] [[Arxiv](https://arxiv.org/abs/2207.08143)]

- Memory-Based Model Editing at Scale. [*2022.06.13*] [[Arxiv](https://arxiv.org/abs/2206.06520)]

- kNN-Prompt: Nearest Neighbor Zero-Shot Inference. [*2022.11.01*] [[Arxiv](https://arxiv.org/abs/2205.13792)]

- Long-term Control for Dialogue Generation: Methods and Evaluation. [*2022.05.15*] [[Arxiv](https://arxiv.org/abs/2205.07352)]

- Efficient Machine Translation Domain Adaptation. [*2022.04.26*] [[Arxiv](https://arxiv.org/abs/2204.12608)]

- A Corpus for Understanding and Generating Moral Stories. [*2022.04.20*] [[Arxiv](https://arxiv.org/abs/2204.09438)]

- Augmenting Pre-trained Language Models with QA-Memory for Open-Domain Question Answering. [*2023.01.23*] [[Arxiv](https://arxiv.org/abs/2204.04581)]

- KGI: An Integrated Framework for Knowledge Intensive Language Tasks. [*2022.09.21*] [[Arxiv](https://arxiv.org/abs/2204.03985)]

- $`k`$NN-NER: Named Entity Recognition with Nearest Neighbor Search. [*2022.03.31*] [[Arxiv](https://arxiv.org/abs/2203.17103)]

- Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks. [*2022.05.14*] [[Arxiv](https://arxiv.org/abs/2112.08688)]

- Reason first, then respond: Modular Generation for Knowledge-infused Dialogue. [*2021.11.09*] [[Arxiv](https://arxiv.org/abs/2111.05204)]

- End-to-End Learning of Flowchart Grounded Task-Oriented Dialogs. [*2021.12.07*] [[Arxiv](https://arxiv.org/abs/2109.07263)]

- Memory and Knowledge Augmented Language Models for Inferring Salience in Long-Form Stories. [*2021.09.14*] [[Arxiv](https://arxiv.org/abs/2109.03754)]

- Beyond Goldfish Memory: Long-Term Open-Domain Conversation. [*2021.07.15*] [[Arxiv](https://arxiv.org/abs/2107.07567)]

- Fine-tune the Entire RAG Architecture (including DPR retriever) for Question-Answering. [*2021.06.21*] [[Arxiv](https://arxiv.org/abs/2106.11517)]

- End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering. [*2021.12.04*] [[Arxiv](https://arxiv.org/abs/2106.05346)]

- Zero-shot Slot Filling with DPR and RAG. [*2021.04.17*] [[Arxiv](https://arxiv.org/abs/2104.08610)]

- Lingke: A Fine-grained Multi-turn Chatbot for Customer Service. [*2018.08.10*] [[Arxiv](https://arxiv.org/abs/1808.03430)]

- Retrieval-Augmented Convolutional Neural Networks for Improved Robustness against Adversarial Examples. [*2018.02.26*] [[Arxiv](https://arxiv.org/abs/1802.09502)]

# Blog

- https://github.com/Wang-Shuo/A-Guide-to-Retrieval-Augmented-LLM

- https://www.anyscale.com/blog/a-comprehensive-guide-for-building-rag-based-llm-applications-part-1

- https://blog.langchain.dev/semi-structured-multi-modal-rag/

- https://acl2023-retrieval-lm.github.io/