{"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/critiquellm-scaling-llm-as-critic-for","title":"CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation","arxiv_id":"2311.18702","date":"2023-11-30","proceeding":null,"authors":["Pei Ke","Bosi Wen","Zhuoer Feng","Xiao Liu","Xuanyu Lei","Jiale Cheng","Shengyuan Wang","Aohan Zeng","Yuxiao Dong","Hongning Wang","Jie Tang","Minlie Huang"],"abstract":"Since the natural language processing (NLP) community started to make large language models (LLMs) act as a critic to evaluate the quality of generated texts, most of the existing works train a critique generation model on the evaluation data labeled by GPT-4's direct prompting. We observe that these models lack the ability to generate informative critiques in both pointwise grading and pairwise comparison especially without references. As a result, their generated critiques cannot provide fine-grained distinguishability on generated texts, causing unsatisfactory evaluation performance. In this paper, we propose a simple yet effective method called Eval-Instruct, which can first acquire pointwise grading critiques with pseudo references and then revise these critiques via multi-path prompting to obtain informative evaluation data in different tasks and settings, including pointwise grading and pairwise comparison with / without references. After fine-tuning on these data, the resulting model CritiqueLLM is empirically shown to outperform ChatGPT and all the open-source baselines and even achieve comparable evaluation performance to GPT-4 in system-level correlations of pointwise grading. We also demonstrate that our generated critiques can act as scalable feedback to further improve the generation quality of strong LLMs like ChatGPT.","url_abs":"https://arxiv.org/abs/2311.18702v2","url_pdf":"https://arxiv.org/pdf/2311.18702v2.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":"critiquellm-scaling-llm-as-critic-for","repo_url":"https://github.com/thu-coai/critiquellm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"critiquellm-scaling-llm-as-critic-for","repo_url":"https://github.com/thudm/alignbench","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2311.18702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.18702"}},"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/thudm/alignbench","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thu-coai/critiquellm","reach":null}],"summary":{"ran_violates":3,"ran_honours":1,"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":5,"samples":[{"code_sha256_prefix":"0164dbe04ac52b71","entry":"extract_label","repo":"thu-coai/critiquellm","repo_kind":"official","path":"evaluation/eval_pairwise.py","file_url":"https://github.com/thu-coai/critiquellm/blob/HEAD/evaluation/eval_pairwise.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0164dbe04ac52b71"}},{"code_sha256_prefix":"a6e47174738c4534","entry":"extract_number","repo":"thu-coai/critiquellm","repo_kind":"official","path":"evaluation/eval_pointwise.py","file_url":"https://github.com/thu-coai/critiquellm/blob/HEAD/evaluation/eval_pointwise.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a6e47174738c4534"}},{"code_sha256_prefix":"d79b3133bb83f30e","entry":"kendall_corr","repo":"thu-coai/critiquellm","repo_kind":"official","path":"evaluation/eval_pointwise.py","file_url":"https://github.com/thu-coai/critiquellm/blob/HEAD/evaluation/eval_pointwise.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d79b3133bb83f30e"}},{"code_sha256_prefix":"6fbfe6608a41dc62","entry":"spearman_corr","repo":"thu-coai/critiquellm","repo_kind":"official","path":"evaluation/eval_pointwise.py","file_url":"https://github.com/thu-coai/critiquellm/blob/HEAD/evaluation/eval_pointwise.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6fbfe6608a41dc62"}},{"code_sha256_prefix":"e4cfccf82f753bc4","entry":"read_data","repo":"thu-coai/critiquellm","repo_kind":"official","path":"inference/inference.py","file_url":"https://github.com/thu-coai/critiquellm/blob/HEAD/inference/inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e4cfccf82f753bc4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}