{"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/reasoning-towards-fairness-mitigating-bias-in","title":"Reasoning Towards Fairness: Mitigating Bias in Language Models through Reasoning-Guided Fine-Tuning","arxiv_id":"2504.05632","date":"2025-04-08","proceeding":null,"authors":["Sanchit Kabra","Akshita Jha","Chandan K. Reddy"],"abstract":"Recent advances in large-scale generative language models have shown that reasoning capabilities can significantly improve model performance across a variety of tasks. However, the impact of reasoning on a model's ability to mitigate stereotypical responses remains largely underexplored. In this work, we investigate the crucial relationship between a model's reasoning ability and fairness, and ask whether improved reasoning capabilities can mitigate harmful stereotypical responses, especially those arising due to shallow or flawed reasoning. We conduct a comprehensive evaluation of multiple open-source LLMs, and find that larger models with stronger reasoning abilities exhibit substantially lower stereotypical bias on existing fairness benchmarks. Building on this insight, we introduce ReGiFT -- Reasoning Guided Fine-Tuning, a novel approach that extracts structured reasoning traces from advanced reasoning models and infuses them into models that lack such capabilities. We use only general-purpose reasoning and do not require any fairness-specific supervision for bias mitigation. Notably, we see that models fine-tuned using ReGiFT not only improve fairness relative to their non-reasoning counterparts but also outperform advanced reasoning models on fairness benchmarks. We also analyze how variations in the correctness of the reasoning traces and their length influence model fairness and their overall performance. Our findings highlight that enhancing reasoning capabilities is an effective, fairness-agnostic strategy for mitigating stereotypical bias caused by reasoning flaws.","url_abs":"https://arxiv.org/abs/2504.05632v2","url_pdf":"https://arxiv.org/pdf/2504.05632v2.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":"reasoning-towards-fairness-mitigating-bias-in","repo_url":"https://github.com/Sanchit-404/Reasoing-Towards-Fairness","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"fairness","task_name":"Fairness"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2504.05632","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.05632"}},"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/Sanchit-404/Reasoing-Towards-Fairness","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"f2ba52311094f608","entry":"create_prompt","repo":"Sanchit-404/Reasoing-Towards-Fairness","repo_kind":"official","path":"scripts/extract_reasoning_traces.py","file_url":"https://github.com/Sanchit-404/Reasoing-Towards-Fairness/blob/HEAD/scripts/extract_reasoning_traces.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f2ba52311094f608"}},{"code_sha256_prefix":"f323d618e2dfa786","entry":"extract_reasoning_and_answer","repo":"Sanchit-404/Reasoing-Towards-Fairness","repo_kind":"official","path":"scripts/evaluate_bbq_outputs.py","file_url":"https://github.com/Sanchit-404/Reasoing-Towards-Fairness/blob/HEAD/scripts/evaluate_bbq_outputs.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f323d618e2dfa786"}},{"code_sha256_prefix":"6b9e5582f91b19d7","entry":"format_prompt","repo":"Sanchit-404/Reasoing-Towards-Fairness","repo_kind":"official","path":"scripts/finetune_on_traces.py","file_url":"https://github.com/Sanchit-404/Reasoing-Towards-Fairness/blob/HEAD/scripts/finetune_on_traces.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6b9e5582f91b19d7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}