{"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/on-policy-fine-grained-knowledge-feedback-for","title":"On-Policy Fine-grained Knowledge Feedback for Hallucination Mitigation","arxiv_id":"2406.12221","date":"2024-06-18","proceeding":null,"authors":["Xueru Wen","Xinyu Lu","Xinyan Guan","Yaojie Lu","Hongyu Lin","Ben He","Xianpei Han","Le Sun"],"abstract":"Hallucination occurs when large language models (LLMs) exhibit behavior that deviates from the boundaries of their knowledge during the response generation process. Previous learning-based methods focus on detecting knowledge boundaries and finetuning models with instance-level feedback, but they suffer from inaccurate signals due to off-policy data sampling and coarse-grained feedback. In this paper, we introduce \\textit{\\b{R}einforcement \\b{L}earning \\b{f}or \\b{H}allucination} (RLFH), a fine-grained feedback-based online reinforcement learning method for hallucination mitigation. Unlike previous learning-based methods, RLFH enables LLMs to explore the boundaries of their internal knowledge and provide on-policy, fine-grained feedback on these explorations. To construct fine-grained feedback for learning reliable generation behavior, RLFH decomposes the outcomes of large models into atomic facts, provides statement-level evaluation signals, and traces back the signals to the tokens of the original responses. Finally, RLFH adopts the online reinforcement algorithm with these token-level rewards to adjust model behavior for hallucination mitigation. For effective on-policy optimization, RLFH also introduces an LLM-based fact assessment framework to verify the truthfulness and helpfulness of atomic facts without human intervention. Experiments on HotpotQA, SQuADv2, and Biography benchmarks demonstrate that RLFH can balance their usage of internal knowledge during the generation process to eliminate the hallucination behavior of LLMs.","url_abs":"https://arxiv.org/abs/2406.12221v1","url_pdf":"https://arxiv.org/pdf/2406.12221v1.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":"on-policy-fine-grained-knowledge-feedback-for","repo_url":"https://github.com/AlignRM/RLFH","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"response-generation","task_name":"Response Generation"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.12221","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12221"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/AlignRM/RLFH","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":"90a4763ce6469af0","entry":"paragraph_rewards_from_labels","repo":"AlignRM/RLFH","repo_kind":"listed","path":"source/feedback/reward.py","file_url":"https://github.com/AlignRM/RLFH/blob/HEAD/source/feedback/reward.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"90a4763ce6469af0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}