{"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/reft-reasoning-with-reinforced-fine-tuning","title":"ReFT: Reasoning with Reinforced Fine-Tuning","arxiv_id":"2401.08967","date":"2024-01-17","proceeding":null,"authors":["Trung Quoc Luong","Xinbo Zhang","Zhanming Jie","Peng Sun","Xiaoran Jin","Hang Li"],"abstract":"One way to enhance the reasoning capability of Large Language Models (LLMs) is to conduct Supervised Fine-Tuning (SFT) using Chain-of-Thought (CoT) annotations. This approach does not show sufficiently strong generalization ability, however, because the training only relies on the given CoT data. In math problem-solving, for example, there is usually only one annotated reasoning path for each question in the training data. Intuitively, it would be better for the algorithm to learn from multiple annotated reasoning paths given a question. To address this issue, we propose a simple yet effective approach called Reinforced Fine-Tuning (ReFT) to enhance the generalizability of learning LLMs for reasoning, with math problem-solving as an example. ReFT first warmups the model with SFT, and then employs on-line reinforcement learning, specifically the PPO algorithm in this paper, to further fine-tune the model, where an abundance of reasoning paths are automatically sampled given the question and the rewards are naturally derived from the ground-truth answers. Extensive experiments on GSM8K, MathQA, and SVAMP datasets show that ReFT significantly outperforms SFT, and the performance can be potentially further boosted by combining inference-time strategies such as majority voting and re-ranking. Note that ReFT obtains the improvement by learning from the same training questions as SFT, without relying on extra or augmented training questions. This indicates a superior generalization ability for ReFT.","url_abs":"https://arxiv.org/abs/2401.08967v3","url_pdf":"https://arxiv.org/pdf/2401.08967v3.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":"reft-reasoning-with-reinforced-fine-tuning","repo_url":"https://github.com/lqtrung1998/mwp_reft","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"gsm8k","task_name":"GSM8K"},{"task_slug":"math","task_name":"Math"},{"task_slug":"re-ranking","task_name":"Re-Ranking"}],"methods":[{"method_slug":"entropy-regularization","method_name":"Entropy Regularization"},{"method_slug":"ppo","method_name":"PPO"},{"method_slug":"sft","method_name":"SFT"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2401.08967","atlas_url":"https://app.syntology.ai/?focus=2401.08967","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.08967"}},"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/lqtrung1998/mwp_reft","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/lqtrung1998/mwp_ReFT","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":14},"by_repo_kind":{"official":{"samples":14,"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":"2bb5bd3526f55ecb","entry":"collate_fn","repo":"lqtrung1998/mwp_ReFT","repo_kind":"official","path":"sampling.py","file_url":"https://github.com/lqtrung1998/mwp_ReFT/blob/HEAD/sampling.py","link_basis":"harvester_set","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":"2bb5bd3526f55ecb"}},{"code_sha256_prefix":"32851be78f5ecd4c","entry":"do_gather","repo":"lqtrung1998/mwp_ReFT","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/lqtrung1998/mwp_ReFT/blob/HEAD/src/utils.py","link_basis":"harvester_set","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":"32851be78f5ecd4c"}},{"code_sha256_prefix":"7fcae9f5e120bafe","entry":"eval_code","repo":"lqtrung1998/mwp_ReFT","repo_kind":"official","path":"src/python_engine.py","file_url":"https://github.com/lqtrung1998/mwp_ReFT/blob/HEAD/src/python_engine.py","link_basis":"harvester_set","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":"7fcae9f5e120bafe"}},{"code_sha256_prefix":"c8164df09b7d7a68","entry":"evaluate_rerank","repo":"lqtrung1998/mwp_ReFT","repo_kind":"official","path":"train_reward_model.py","file_url":"https://github.com/lqtrung1998/mwp_ReFT/blob/HEAD/train_reward_model.py","link_basis":"harvester_set","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":"c8164df09b7d7a68"}},{"code_sha256_prefix":"f21a5f0d5bae0c14","entry":"floatify","repo":"lqtrung1998/mwp_ReFT","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/lqtrung1998/mwp_ReFT/blob/HEAD/src/utils.py","link_basis":"harvester_set","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":"f21a5f0d5bae0c14"}},{"code_sha256_prefix":"c3b86a3bceec86cd","entry":"is_numeric","repo":"lqtrung1998/mwp_ReFT","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/lqtrung1998/mwp_ReFT/blob/HEAD/src/utils.py","link_basis":"harvester_set","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":"c3b86a3bceec86cd"}},{"code_sha256_prefix":"4d434f6e5fd591b5","entry":"prepare_datasets_and_data_loaders","repo":"lqtrung1998/mwp_ReFT","repo_kind":"official","path":"train_reward_model.py","file_url":"https://github.com/lqtrung1998/mwp_ReFT/blob/HEAD/train_reward_model.py","link_basis":"harvester_set","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":"4d434f6e5fd591b5"}},{"code_sha256_prefix":"9f0489fe01df9539","entry":"prepare_datasets_and_data_loaders","repo":"lqtrung1998/mwp_ReFT","repo_kind":"official","path":"train_sl_model.py","file_url":"https://github.com/lqtrung1998/mwp_ReFT/blob/HEAD/train_sl_model.py","link_basis":"harvester_set","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":"9f0489fe01df9539"}},{"code_sha256_prefix":"449e6a4081f8d019","entry":"prepare_datasets_and_data_loaders","repo":"lqtrung1998/mwp_ReFT","repo_kind":"official","path":"train_rl_reft.py","file_url":"https://github.com/lqtrung1998/mwp_ReFT/blob/HEAD/train_rl_reft.py","link_basis":"harvester_set","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":"449e6a4081f8d019"}},{"code_sha256_prefix":"01e9a5c8f882c073","entry":"prepare_datasets_and_data_loaders","repo":"lqtrung1998/mwp_ReFT","repo_kind":"official","path":"train_rl_sl.py","file_url":"https://github.com/lqtrung1998/mwp_ReFT/blob/HEAD/train_rl_sl.py","link_basis":"harvester_set","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":"01e9a5c8f882c073"}},{"code_sha256_prefix":"d0eff44d0f627c24","entry":"prepare_datasets_and_data_loaders","repo":"lqtrung1998/mwp_ReFT","repo_kind":"official","path":"train_sft_model.py","file_url":"https://github.com/lqtrung1998/mwp_ReFT/blob/HEAD/train_sft_model.py","link_basis":"harvester_set","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":"d0eff44d0f627c24"}},{"code_sha256_prefix":"8b9f60df8d2c8a82","entry":"process_code","repo":"lqtrung1998/mwp_ReFT","repo_kind":"official","path":"src/python_engine.py","file_url":"https://github.com/lqtrung1998/mwp_ReFT/blob/HEAD/src/python_engine.py","link_basis":"harvester_set","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":"8b9f60df8d2c8a82"}},{"code_sha256_prefix":"951fe709737c50b9","entry":"tokenize_fn","repo":"lqtrung1998/mwp_ReFT","repo_kind":"official","path":"sampling.py","file_url":"https://github.com/lqtrung1998/mwp_ReFT/blob/HEAD/sampling.py","link_basis":"harvester_set","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":"951fe709737c50b9"}},{"code_sha256_prefix":"d3b8681876990bfa","entry":"train_one_epoch","repo":"lqtrung1998/mwp_ReFT","repo_kind":"official","path":"train_reward_model.py","file_url":"https://github.com/lqtrung1998/mwp_ReFT/blob/HEAD/train_reward_model.py","link_basis":"harvester_set","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":"d3b8681876990bfa"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}