{"id":18887110,"url":"https://github.com/thunlp-mt/ric","last_synced_at":"2025-10-18T23:57:23.433Z","repository":{"id":255342710,"uuid":"803268903","full_name":"THUNLP-MT/RiC","owner":"THUNLP-MT","description":null,"archived":false,"fork":false,"pushed_at":"2024-08-29T10:55:23.000Z","size":789,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":4,"default_branch":"main","last_synced_at":"2024-12-31T05:18:56.912Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/THUNLP-MT.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","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":"2024-05-20T12:02:30.000Z","updated_at":"2024-11-19T15:25:04.000Z","dependencies_parsed_at":"2024-08-29T12:07:07.195Z","dependency_job_id":"07d4e1c3-7112-4a96-b9af-fd1584dfce6d","html_url":"https://github.com/THUNLP-MT/RiC","commit_stats":null,"previous_names":["thunlp-mt/ric"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/THUNLP-MT%2FRiC","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/THUNLP-MT%2FRiC/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/THUNLP-MT%2FRiC/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/THUNLP-MT%2FRiC/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/THUNLP-MT","download_url":"https://codeload.github.com/THUNLP-MT/RiC/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239859563,"owners_count":19708863,"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":[],"created_at":"2024-11-08T07:34:14.070Z","updated_at":"2025-10-18T23:57:18.394Z","avatar_url":"https://github.com/THUNLP-MT.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Reasoning in Conversation: Solving Subjective Tasks through Dialogue Simulation for Large Language Models\r\n\r\n**❗❗REPO UNDER CONSTRUCTION❗❗**\r\n\r\n[**📖 Paper**](https://aclanthology.org/2024.acl-long.844/)\r\n\r\nThis repo contains the code for paper [Reasoning in Conversation: Solving Subjective Tasks through Dialogue Simulation for Large Language Models](https://aclanthology.org/2024.acl-long.844/).\r\n\r\n## Introduction\r\n\r\nCompared to objective tasks, subjective tasks focus more on interpretation or emotional response rather than a universally accepted reasoning pathway. Based on the characteristics of the tasks and the strong dialogue-generation capabilities of LLMs, we propose RiC (Reasoning in Conversation), a method that focuses on solving subjective tasks through dialogue simulation.\r\n\r\nThe motivation of RiC is to mine useful contextual information by simulating dialogues instead of supplying CoT style rationales, thereby offering potential useful knowledge behind dialogues for giving the final answers. We evaluate both API-based and open-source LLMs including GPT-4, ChatGPT, and OpenChat across twelve tasks. Experimental results show that RiC can yield significant improvement compared with various baselines.\r\n\r\n\u003ccenter\u003e\u003cimg src=\"./images/intro.jpg\" alt=\"RiC\" width=\"50%\"\u003e\u003c/center\u003e\r\n\r\n## Experiments\r\n\r\nMain results in zero-shot setup.\r\n\r\n\u003ccenter\u003e\u003cimg src=\"./images/exp_1.jpg\" alt=\"Zero-shot Results\" width=\"100%\"\u003e\u003c/center\u003e\r\n\r\nPerformance of baselines and our RiC method by using different numbers of demonstrations.\r\n\r\n\u003ccenter\u003e\u003cimg src=\"./images/exp_2.jpg\" alt=\"Few-shot Results\" width=\"50%\"\u003e\u003c/center\u003e\r\n\r\n## Installation\r\n\r\n*Comming Soon!*\r\n\r\n## Run RiC\r\n\r\n*Comming Soon!*\r\n\r\n## Citation\r\n\r\n```bibtex\r\n@inproceedings{wang-etal-2024-reasoning,\r\n    title = \"Reasoning in Conversation: Solving Subjective Tasks through Dialogue Simulation for Large Language Models\",\r\n    author = \"Wang, Xiaolong  and\r\n      Wang, Yile  and\r\n      Zhang, Yuanchi  and\r\n      Luo, Fuwen  and\r\n      Li, Peng  and\r\n      Sun, Maosong  and\r\n      Liu, Yang\",\r\n    editor = \"Ku, Lun-Wei  and\r\n      Martins, Andre  and\r\n      Srikumar, Vivek\",\r\n    booktitle = \"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)\",\r\n    month = aug,\r\n    year = \"2024\",\r\n    address = \"Bangkok, Thailand\",\r\n    publisher = \"Association for Computational Linguistics\",\r\n    url = \"https://aclanthology.org/2024.acl-long.844\",\r\n    pages = \"15880--15893\",\r\n}\r\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthunlp-mt%2Fric","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fthunlp-mt%2Fric","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthunlp-mt%2Fric/lists"}