{"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/llms-are-biased-towards-output-formats","title":"LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs","arxiv_id":"2408.08656","date":"2024-08-16","proceeding":null,"authors":["Do Xuan Long","Hai Nguyen Ngoc","Tiviatis Sim","Hieu Dao","Shafiq Joty","Kenji Kawaguchi","Nancy F. Chen","Min-Yen Kan"],"abstract":"We present the first systematic evaluation examining format bias in performance of large language models (LLMs). Our approach distinguishes between two categories of an evaluation metric under format constraints to reliably and accurately assess performance: one measures performance when format constraints are adhered to, while the other evaluates performance regardless of constraint adherence. We then define a metric for measuring the format bias of LLMs and establish effective strategies to reduce it. Subsequently, we present our empirical format bias evaluation spanning four commonly used categories -- multiple-choice question-answer, wrapping, list, and mapping -- covering 15 widely-used formats. Our evaluation on eight generation tasks uncovers significant format bias across state-of-the-art LLMs. We further discover that improving the format-instruction following capabilities of LLMs across formats potentially reduces format bias. Based on our evaluation findings, we study prompting and fine-tuning with synthesized format data techniques to mitigate format bias. Our methods successfully reduce the variance in ChatGPT's performance among wrapping formats from 235.33 to 0.71 (%$^2$).","url_abs":"https://arxiv.org/abs/2408.08656v1","url_pdf":"https://arxiv.org/pdf/2408.08656v1.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":"llms-are-biased-towards-output-formats","repo_url":"https://github.com/dxlong2000/FormatEval","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"multiple-choice","task_name":"Multiple-choice"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2408.08656","atlas_url":"https://app.syntology.ai/?focus=2408.08656","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.08656"}},"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/dxlong2000/FormatEval","reach":{"status":"ok"}}],"summary":{"ran":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":"10163f07fc4024b3","entry":"check_bolding","repo":"dxlong2000/FormatEval","repo_kind":"official","path":"src/output/evaluate_generation_SystematicF1_FI.py","file_url":"https://github.com/dxlong2000/FormatEval/blob/HEAD/src/output/evaluate_generation_SystematicF1_FI.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"10163f07fc4024b3"}},{"code_sha256_prefix":"3a21d477b1ff88ad","entry":"check_free_form_follow","repo":"dxlong2000/FormatEval","repo_kind":"official","path":"src/output/evaluate_generation_SystematicF1_FI.py","file_url":"https://github.com/dxlong2000/FormatEval/blob/HEAD/src/output/evaluate_generation_SystematicF1_FI.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3a21d477b1ff88ad"}},{"code_sha256_prefix":"967e049ba4d608b0","entry":"check_mcq_answer","repo":"dxlong2000/FormatEval","repo_kind":"official","path":"src/output/evaluate_generation_SystematicF1_FI.py","file_url":"https://github.com/dxlong2000/FormatEval/blob/HEAD/src/output/evaluate_generation_SystematicF1_FI.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"967e049ba4d608b0"}},{"code_sha256_prefix":"306480175aba7766","entry":"compute_variance","repo":"dxlong2000/FormatEval","repo_kind":"official","path":"EvalData/sampling.py","file_url":"https://github.com/dxlong2000/FormatEval/blob/HEAD/EvalData/sampling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"306480175aba7766"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}