{"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/navigating-noisy-feedback-enhancing","title":"Navigating Noisy Feedback: Enhancing Reinforcement Learning with Error-Prone Language Models","arxiv_id":"2410.17389","date":"2024-10-22","proceeding":null,"authors":["MuHan Lin","Shuyang Shi","Yue Guo","Behdad Chalaki","Vaishnav Tadiparthi","Ehsan Moradi Pari","Simon Stepputtis","Joseph Campbell","Katia Sycara"],"abstract":"The correct specification of reward models is a well-known challenge in reinforcement learning. Hand-crafted reward functions often lead to inefficient or suboptimal policies and may not be aligned with user values. Reinforcement learning from human feedback is a successful technique that can mitigate such issues, however, the collection of human feedback can be laborious. Recent works have solicited feedback from pre-trained large language models rather than humans to reduce or eliminate human effort, however, these approaches yield poor performance in the presence of hallucination and other errors. This paper studies the advantages and limitations of reinforcement learning from large language model feedback and proposes a simple yet effective method for soliciting and applying feedback as a potential-based shaping function. We theoretically show that inconsistent rankings, which approximate ranking errors, lead to uninformative rewards with our approach. Our method empirically improves convergence speed and policy returns over commonly used baselines even with significant ranking errors, and eliminates the need for complex post-processing of reward functions.","url_abs":"https://arxiv.org/abs/2410.17389v1","url_pdf":"https://arxiv.org/pdf/2410.17389v1.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":"navigating-noisy-feedback-enhancing","repo_url":"https://github.com/sy-shi/RLAIF_ScoreDiff","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.17389","atlas_url":"https://app.syntology.ai/?focus=2410.17389","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17389"}},"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/sy-shi/RLAIF_ScoreDiff","reach":null}],"summary":{"ran_honours":2,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":4,"samples":[{"code_sha256_prefix":"fc93bc090f3a63c7","entry":"custom_loss","repo":"sy-shi/RLAIF_ScoreDiff","repo_kind":"official","path":"train_rm.py","file_url":"https://github.com/sy-shi/RLAIF_ScoreDiff/blob/HEAD/train_rm.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fc93bc090f3a63c7"}},{"code_sha256_prefix":"aaeecfe1ef8324e7","entry":"lr_lambda_selector","repo":"sy-shi/RLAIF_ScoreDiff","repo_kind":"official","path":"train_rm.py","file_url":"https://github.com/sy-shi/RLAIF_ScoreDiff/blob/HEAD/train_rm.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"aaeecfe1ef8324e7"}},{"code_sha256_prefix":"f0e515a163e67f9f","entry":"manhattan_distance","repo":"sy-shi/RLAIF_ScoreDiff","repo_kind":"official","path":"generate_ranking_data.py","file_url":"https://github.com/sy-shi/RLAIF_ScoreDiff/blob/HEAD/generate_ranking_data.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f0e515a163e67f9f"}},{"code_sha256_prefix":"dd0ba84e7526171f","entry":"train","repo":"sy-shi/RLAIF_ScoreDiff","repo_kind":"official","path":"train_rm.py","file_url":"https://github.com/sy-shi/RLAIF_ScoreDiff/blob/HEAD/train_rm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dd0ba84e7526171f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}