{"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/calibrating-llm-based-evaluator","title":"Calibrating LLM-Based Evaluator","arxiv_id":"2309.13308","date":"2023-09-23","proceeding":null,"authors":["Yuxuan Liu","Tianchi Yang","Shaohan Huang","Zihan Zhang","Haizhen Huang","Furu Wei","Weiwei Deng","Feng Sun","Qi Zhang"],"abstract":"Recent advancements in large language models (LLMs) on language modeling and emergent capabilities make them a promising reference-free evaluator of natural language generation quality, and a competent alternative to human evaluation. However, hindered by the closed-source or high computational demand to host and tune, there is a lack of practice to further calibrate an off-the-shelf LLM-based evaluator towards better human alignment. In this work, we propose AutoCalibrate, a multi-stage, gradient-free approach to automatically calibrate and align an LLM-based evaluator toward human preference. Instead of explicitly modeling human preferences, we first implicitly encompass them within a set of human labels. Then, an initial set of scoring criteria is drafted by the language model itself, leveraging in-context learning on different few-shot examples. To further calibrate this set of criteria, we select the best performers and re-draft them with self-refinement. Our experiments on multiple text quality evaluation datasets illustrate a significant improvement in correlation with expert evaluation through calibration. Our comprehensive qualitative analysis conveys insightful intuitions and observations on the essence of effective scoring criteria.","url_abs":"https://arxiv.org/abs/2309.13308v1","url_pdf":"https://arxiv.org/pdf/2309.13308v1.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":"calibrating-llm-based-evaluator","repo_url":"https://github.com/FKIRSTE/emnlp2024-personalized-meeting-sum","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.13308","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.13308"}},"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/FKIRSTE/emnlp2024-personalized-meeting-sum","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":10},"by_repo_kind":{"listed":{"samples":10,"ran":0,"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":"94c7115d7f31a49f","entry":"askgptcomplex","repo":"FKIRSTE/emnlp2024-personalized-meeting-sum","repo_kind":"listed","path":"code/chatwithmodels.py","file_url":"https://github.com/FKIRSTE/emnlp2024-personalized-meeting-sum/blob/HEAD/code/chatwithmodels.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":"94c7115d7f31a49f"}},{"code_sha256_prefix":"7fc2fb12340dc132","entry":"build_prompt","repo":"FKIRSTE/emnlp2024-personalized-meeting-sum","repo_kind":"listed","path":"baseline/G-all.py","file_url":"https://github.com/FKIRSTE/emnlp2024-personalized-meeting-sum/blob/HEAD/baseline/G-all.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":"7fc2fb12340dc132"}},{"code_sha256_prefix":"101c21be672b0d7b","entry":"build_prompt","repo":"FKIRSTE/emnlp2024-personalized-meeting-sum","repo_kind":"listed","path":"baseline/OUT-P-all.py","file_url":"https://github.com/FKIRSTE/emnlp2024-personalized-meeting-sum/blob/HEAD/baseline/OUT-P-all.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":"101c21be672b0d7b"}},{"code_sha256_prefix":"8d97761d2b2796e5","entry":"build_prompt","repo":"FKIRSTE/emnlp2024-personalized-meeting-sum","repo_kind":"listed","path":"baseline/P-all.py","file_url":"https://github.com/FKIRSTE/emnlp2024-personalized-meeting-sum/blob/HEAD/baseline/P-all.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":"8d97761d2b2796e5"}},{"code_sha256_prefix":"228f2ec1f2816b90","entry":"build_prompt","repo":"FKIRSTE/emnlp2024-personalized-meeting-sum","repo_kind":"listed","path":"baseline/P-none.py","file_url":"https://github.com/FKIRSTE/emnlp2024-personalized-meeting-sum/blob/HEAD/baseline/P-none.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":"228f2ec1f2816b90"}},{"code_sha256_prefix":"0eb0e62e6b82b1e2","entry":"concat_items","repo":"FKIRSTE/emnlp2024-personalized-meeting-sum","repo_kind":"listed","path":"baseline/G-all.py","file_url":"https://github.com/FKIRSTE/emnlp2024-personalized-meeting-sum/blob/HEAD/baseline/G-all.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":"0eb0e62e6b82b1e2"}},{"code_sha256_prefix":"8a8dfaa31b947179","entry":"concat_ppt","repo":"FKIRSTE/emnlp2024-personalized-meeting-sum","repo_kind":"listed","path":"baseline/G-all.py","file_url":"https://github.com/FKIRSTE/emnlp2024-personalized-meeting-sum/blob/HEAD/baseline/G-all.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":"8a8dfaa31b947179"}},{"code_sha256_prefix":"9ac9ea4d2670b185","entry":"get_modified_transcript","repo":"FKIRSTE/emnlp2024-personalized-meeting-sum","repo_kind":"listed","path":"code/personalized_summary.py","file_url":"https://github.com/FKIRSTE/emnlp2024-personalized-meeting-sum/blob/HEAD/code/personalized_summary.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":"9ac9ea4d2670b185"}},{"code_sha256_prefix":"95a25687c9be827c","entry":"gpt_model_call","repo":"FKIRSTE/emnlp2024-personalized-meeting-sum","repo_kind":"listed","path":"code/chatwithmodels.py","file_url":"https://github.com/FKIRSTE/emnlp2024-personalized-meeting-sum/blob/HEAD/code/chatwithmodels.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":"95a25687c9be827c"}},{"code_sha256_prefix":"9d8c8ab4f7f554c2","entry":"load_config","repo":"FKIRSTE/emnlp2024-personalized-meeting-sum","repo_kind":"listed","path":"baseline/config_loader.py","file_url":"https://github.com/FKIRSTE/emnlp2024-personalized-meeting-sum/blob/HEAD/baseline/config_loader.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":"9d8c8ab4f7f554c2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}