{"id":20779455,"url":"https://github.com/freedomintelligence/chatgpt-detection-pr-hppt","last_synced_at":"2025-04-30T19:42:23.984Z","repository":{"id":183342210,"uuid":"667710549","full_name":"FreedomIntelligence/ChatGPT-Detection-PR-HPPT","owner":"FreedomIntelligence","description":"Codes and dataset for the paper: Is ChatGPT Involved in Texts? Measure the Polish Ratio to Detect ChatGPT-Generated Text","archived":false,"fork":false,"pushed_at":"2024-08-01T14:31:50.000Z","size":34429,"stargazers_count":9,"open_issues_count":3,"forks_count":0,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-03-30T19:22:15.815Z","etag":null,"topics":["chatgpt-detection","large-language-models","polish-ratio"],"latest_commit_sha":null,"homepage":"","language":"Python","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/FreedomIntelligence.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}},"created_at":"2023-07-18T06:18:27.000Z","updated_at":"2024-11-21T17:09:00.000Z","dependencies_parsed_at":"2024-08-01T16:19:33.782Z","dependency_job_id":null,"html_url":"https://github.com/FreedomIntelligence/ChatGPT-Detection-PR-HPPT","commit_stats":null,"previous_names":["clement1290/chatgpt-detection-pr-hppt","freedomintelligence/chatgpt-detection-pr-hppt"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FreedomIntelligence%2FChatGPT-Detection-PR-HPPT","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FreedomIntelligence%2FChatGPT-Detection-PR-HPPT/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FreedomIntelligence%2FChatGPT-Detection-PR-HPPT/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FreedomIntelligence%2FChatGPT-Detection-PR-HPPT/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/FreedomIntelligence","download_url":"https://codeload.github.com/FreedomIntelligence/ChatGPT-Detection-PR-HPPT/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251771624,"owners_count":21641288,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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"}},"keywords":["chatgpt-detection","large-language-models","polish-ratio"],"created_at":"2024-11-17T13:28:00.503Z","updated_at":"2025-04-30T19:42:23.958Z","avatar_url":"https://github.com/FreedomIntelligence.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ChatGPT-Detection-PR-HPPT \nThis our dataset and code for the paper: [Is ChatGPT Involved in Texts? Measure the Polish Ratio to Detect ChatGPT-Generated Text](https://www.nowpublishers.com/article/Details/SIP-2023-0050)\n![The overall design of our method.](image.png)\n\n\n# Guideline\n\nThe detector is a Roberta for classification model with labels (0: human, 1:ChatGPT-involved).\n\nIf you want to train it, follow these steps:\n\n1. install the environment\n\n```bash\npip install -r requirements.txt\n```\n\n2. train a detector\n```bash\ncd Detector\n```\n```bash\npython train.py\n```\n\nIt is also all right for you to change some setting in the code.\n\n3. get the detector\n\nThe ```best_model.pt``` is the trained detector.\n\nYou can test the custom sample in text_test.txt (only three examples in it):\n\n```bash\npython inference.py\n```\n\nIf you do not want to train the model, we provide our trained detector on HPPT: [Trained Detector on Google driver](https://drive.google.com/file/d/10qTNMj4Fo1GwNXhWtlM5RZK5VXsgOsoD/view?usp=drive_link) and [Trained Detector on Huggingface](https://huggingface.co/FreedomIntelligence/ChatGPT-Detection-PR-HPPT).\n\n4. train a model to get polish ratio\n```bash\ncd ../PR_reg\n```\n\n```bash\npython train.py\n```\n\nWe also provide the trained PR model: [Trained PR model](https://drive.google.com/file/d/1WquVC6ei-gkNE_oHm9W6N5iR8gu5XjLB/view?usp=drive_link)\n\n# Citation\nYou are welcome to use our dataset and models. \nFor citation following BibTex entry: \n```bash\n@article{yang2023chatgpt,\n  title={Is chatgpt involved in texts? measure the polish ratio to detect chatgpt-generated text},\n  author={Yang, Lingyi and Jiang, Feng and Li, Haizhou},\n  journal={APSIPA Transactions on Signal and Information Processing},\n  volume={13},\n  number={2},\n  publisher={Now Publishers, Inc.}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffreedomintelligence%2Fchatgpt-detection-pr-hppt","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffreedomintelligence%2Fchatgpt-detection-pr-hppt","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffreedomintelligence%2Fchatgpt-detection-pr-hppt/lists"}