{"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/likelihood-based-mitigation-of-evaluation","title":"Likelihood-based Mitigation of Evaluation Bias in Large Language Models","arxiv_id":"2402.15987","date":"2024-02-25","proceeding":null,"authors":["Masanari Ohi","Masahiro Kaneko","Ryuto Koike","Mengsay Loem","Naoaki Okazaki"],"abstract":"Large Language Models (LLMs) are widely used to evaluate natural language generation tasks as automated metrics. However, the likelihood, a measure of LLM's plausibility for a sentence, can vary due to superficial differences in sentences, such as word order and sentence structure. It is therefore possible that there might be a likelihood bias if LLMs are used for evaluation: they might overrate sentences with higher likelihoods while underrating those with lower likelihoods. In this paper, we investigate the presence and impact of likelihood bias in LLM-based evaluators. We also propose a method to mitigate the likelihood bias. Our method utilizes highly biased instances as few-shot examples for in-context learning. Our experiments in evaluating the data-to-text and grammatical error correction tasks reveal that several LLMs we test display a likelihood bias. Furthermore, our proposed method successfully mitigates this bias, also improving evaluation performance (in terms of correlation of models with human scores) significantly.","url_abs":"https://arxiv.org/abs/2402.15987v3","url_pdf":"https://arxiv.org/pdf/2402.15987v3.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":"likelihood-based-mitigation-of-evaluation","repo_url":"https://github.com/stjohn2007/likelihood_bias","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"grammatical-error-correction","task_name":"Grammatical Error Correction"},{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.15987","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15987"}},"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/stjohn2007/likelihood_bias","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":4,"unverified":1},"by_repo_kind":{"official":{"samples":5,"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":0,"samples":[{"code_sha256_prefix":"1e970d5c38fd66b2","entry":"load_llama2","repo":"stjohn2007/likelihood_bias","repo_kind":"official","path":"src/utils/llama2_util.py","file_url":"https://github.com/stjohn2007/likelihood_bias/blob/HEAD/src/utils/llama2_util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1e970d5c38fd66b2"}},{"code_sha256_prefix":"974d9505453432f9","entry":"rescale_human_score","repo":"stjohn2007/likelihood_bias","repo_kind":"official","path":"src/utils/data_util.py","file_url":"https://github.com/stjohn2007/likelihood_bias/blob/HEAD/src/utils/data_util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"974d9505453432f9"}},{"code_sha256_prefix":"01a25bf8a886c5e4","entry":"rescale_score","repo":"stjohn2007/likelihood_bias","repo_kind":"official","path":"calc_cor_after_mitigation.py","file_url":"https://github.com/stjohn2007/likelihood_bias/blob/HEAD/calc_cor_after_mitigation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"01a25bf8a886c5e4"}},{"code_sha256_prefix":"514301dfa39440a8","entry":"rescale_scores","repo":"stjohn2007/likelihood_bias","repo_kind":"official","path":"src/utils/prompt_util.py","file_url":"https://github.com/stjohn2007/likelihood_bias/blob/HEAD/src/utils/prompt_util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"514301dfa39440a8"}},{"code_sha256_prefix":"85fcc9417e43864b","entry":"evaluator_openai_geval_score","repo":"stjohn2007/likelihood_bias","repo_kind":"official","path":"src/evaluator.py","file_url":"https://github.com/stjohn2007/likelihood_bias/blob/HEAD/src/evaluator.py","link_basis":"first_harvest_node","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":"85fcc9417e43864b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}