{"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/judgelm-fine-tuned-large-language-models-are","title":"JudgeLM: Fine-tuned Large Language Models are Scalable Judges","arxiv_id":"2310.17631","date":"2023-10-26","proceeding":null,"authors":["Lianghui Zhu","Xinggang Wang","Xinlong Wang"],"abstract":"Evaluating Large Language Models (LLMs) in open-ended scenarios is challenging because existing benchmarks and metrics can not measure them comprehensively. To address this problem, we propose to fine-tune LLMs as scalable judges (JudgeLM) to evaluate LLMs efficiently and effectively in open-ended benchmarks. We first propose a comprehensive, large-scale, high-quality dataset containing task seeds, LLMs-generated answers, and GPT-4-generated judgments for fine-tuning high-performance judges, as well as a new benchmark for evaluating the judges. We train JudgeLM at different scales from 7B, 13B, to 33B parameters, and conduct a systematic analysis of its capabilities and behaviors. We then analyze the key biases in fine-tuning LLM as a judge and consider them as position bias, knowledge bias, and format bias. To address these issues, JudgeLM introduces a bag of techniques including swap augmentation, reference support, and reference drop, which clearly enhance the judge's performance. JudgeLM obtains the state-of-the-art judge performance on both the existing PandaLM benchmark and our proposed new benchmark. Our JudgeLM is efficient and the JudgeLM-7B only needs 3 minutes to judge 5K samples with 8 A100 GPUs. JudgeLM obtains high agreement with the teacher judge, achieving an agreement exceeding 90% that even surpasses human-to-human agreement. JudgeLM also demonstrates extended capabilities in being judges of the single answer, multimodal models, multiple answers, and multi-turn chat.","url_abs":"https://arxiv.org/abs/2310.17631v1","url_pdf":"https://arxiv.org/pdf/2310.17631v1.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":"judgelm-fine-tuned-large-language-models-are","repo_url":"https://github.com/baaivision/judgelm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"judgelm-fine-tuned-large-language-models-are","repo_url":"https://github.com/hitz-zentroa/eval-MCG-COLING-2025","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.17631","atlas_url":"https://app.syntology.ai/?focus=2310.17631","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.17631"}},"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/baaivision/judgelm","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hitz-zentroa/eval-MCG-COLING-2025","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"ran_honours":1,"unverified":2},"by_repo_kind":{"listed":{"samples":6,"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":"80dde39da1ba3708","entry":"compress","repo":"hitz-zentroa/eval-MCG-COLING-2025","repo_kind":"listed","path":"evaluation/JudgeLM-main/judgelm/model/compression.py","file_url":"https://github.com/hitz-zentroa/eval-MCG-COLING-2025/blob/HEAD/evaluation/JudgeLM-main/judgelm/model/compression.py","link_basis":"harvester_set","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":"80dde39da1ba3708"}},{"code_sha256_prefix":"b904d307320eb547","entry":"filt_pred_score_list_by_gt_score_list","repo":"hitz-zentroa/eval-MCG-COLING-2025","repo_kind":"listed","path":"evaluation/JudgeLM-main/judgelm/llm_judge/eval_model_judgement.py","file_url":"https://github.com/hitz-zentroa/eval-MCG-COLING-2025/blob/HEAD/evaluation/JudgeLM-main/judgelm/llm_judge/eval_model_judgement.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b904d307320eb547"}},{"code_sha256_prefix":"c5824da57107fe8c","entry":"get_compressed_list","repo":"hitz-zentroa/eval-MCG-COLING-2025","repo_kind":"listed","path":"evaluation/JudgeLM-main/judgelm/model/compression.py","file_url":"https://github.com/hitz-zentroa/eval-MCG-COLING-2025/blob/HEAD/evaluation/JudgeLM-main/judgelm/model/compression.py","link_basis":"harvester_set","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":"c5824da57107fe8c"}},{"code_sha256_prefix":"dc21db7cf25bfe72","entry":"process_response","repo":"hitz-zentroa/eval-MCG-COLING-2025","repo_kind":"listed","path":"evaluation/JudgeLM-main/judgelm/model/chatglm_model.py","file_url":"https://github.com/hitz-zentroa/eval-MCG-COLING-2025/blob/HEAD/evaluation/JudgeLM-main/judgelm/model/chatglm_model.py","link_basis":"harvester_set","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":"dc21db7cf25bfe72"}},{"code_sha256_prefix":"d3f7074a99b4f5dd","entry":"get_conv_template","repo":"hitz-zentroa/eval-MCG-COLING-2025","repo_kind":"listed","path":"evaluation/JudgeLM-main/judgelm/conversation.py","file_url":"https://github.com/hitz-zentroa/eval-MCG-COLING-2025/blob/HEAD/evaluation/JudgeLM-main/judgelm/conversation.py","link_basis":"harvester_set","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":"d3f7074a99b4f5dd"}},{"code_sha256_prefix":"8cd841084972921e","entry":"load_compress_model","repo":"hitz-zentroa/eval-MCG-COLING-2025","repo_kind":"listed","path":"evaluation/JudgeLM-main/judgelm/model/compression.py","file_url":"https://github.com/hitz-zentroa/eval-MCG-COLING-2025/blob/HEAD/evaluation/JudgeLM-main/judgelm/model/compression.py","link_basis":"harvester_set","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":"8cd841084972921e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}