{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/openchat-advancing-open-source-language","title":"OpenChat: Advancing Open-source Language Models with Mixed-Quality Data","arxiv_id":"2309.11235","date":"2023-09-20","proceeding":null,"authors":["Guan Wang","Sijie Cheng","Xianyuan Zhan","Xiangang Li","Sen Song","Yang Liu"],"abstract":"Nowadays, open-source large language models like LLaMA have emerged. Recent developments have incorporated supervised fine-tuning (SFT) and reinforcement learning fine-tuning (RLFT) to align these models with human goals. However, SFT methods treat all training data with mixed quality equally, while RLFT methods require high-quality pairwise or ranking-based preference data. In this study, we present a novel framework, named OpenChat, to advance open-source language models with mixed-quality data. Specifically, we consider the general SFT training data, consisting of a small amount of expert data mixed with a large proportion of sub-optimal data, without any preference labels. We propose the C(onditioned)-RLFT, which regards different data sources as coarse-grained reward labels and learns a class-conditioned policy to leverage complementary data quality information. Interestingly, the optimal policy in C-RLFT can be easily solved through single-stage, RL-free supervised learning, which is lightweight and avoids costly human preference labeling. Through extensive experiments on three standard benchmarks, our openchat-13b fine-tuned with C-RLFT achieves the highest average performance among all 13b open-source language models. Moreover, we use AGIEval to validate the model generalization performance, in which only openchat-13b surpasses the base model. Finally, we conduct a series of analyses to shed light on the effectiveness and robustness of OpenChat. Our code, data, and models are publicly available at https://github.com/imoneoi/openchat and https://huggingface.co/openchat.","url_abs":"https://arxiv.org/abs/2309.11235v2","url_pdf":"https://arxiv.org/pdf/2309.11235v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"openchat-advancing-open-source-language","repo_url":"https://github.com/imoneoi/openchat","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"arithmetic-reasoning","task_name":"Arithmetic Reasoning"},{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"math-word-problem-solving","task_name":"Math Word Problem Solving"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/arithmetic-reasoning-on-gsm8k","task":"Arithmetic Reasoning","dataset":"GSM8K","model":"OpenChat-3.5 7B","rank_in_archive_order":81,"of":164,"metrics":{"Accuracy":"77.3","Parameters (Billion)":"7"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"OpenChat-3.5-1210 7B","rank_in_archive_order":91,"of":135,"metrics":{"Accuracy":"28.9","Parameters (Billions)":"7"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"OpenChat-3.5 7B","rank_in_archive_order":92,"of":135,"metrics":{"Accuracy":"28.6","Parameters (Billions)":"7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2309.11235","atlas_url":"https://app.syntology.ai/?focus=2309.11235","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.11235"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/imoneoi/openchat","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"d8a0d063f54a50e2","entry":"tokenize_questions","repo":"imoneoi/openchat","repo_kind":"official","path":"ochat/evaluation/run_eval.py","file_url":"https://github.com/imoneoi/openchat/blob/HEAD/ochat/evaluation/run_eval.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d8a0d063f54a50e2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}