{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LG455YP7SFM72MNR643XXCVUON","short_pith_number":"pith:LG455YP7","schema_version":"1.0","canonical_sha256":"59b9dee1ff9159fd31b1f7377b8ab47374573b1503480b7528d03d14ca66f03c","source":{"kind":"arxiv","id":"2311.18702","version":2},"attestation_state":"computed","paper":{"title":"CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aohan Zeng, Bosi Wen, Hongning Wang, Jiale Cheng, Jie Tang, Minlie Huang, Pei Ke, Shengyuan Wang, Xiao Liu, Xuanyu Lei, Yuxiao Dong, Zhuoer Feng","submitted_at":"2023-11-30T16:52:42Z","abstract_excerpt":"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 thi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2311.18702","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-30T16:52:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d2820354a47908b08163eeded4a1a8d40018d93ca10cb17cb6ba66e52561eda5","abstract_canon_sha256":"6aa0b4ead29ecf82781ebae19cd6e5ebbc2fd0a5de755446b113c6cfd660c113"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:44.673218Z","signature_b64":"3/x6SFrLjKEbSVAn7BeZTC0tcwfNiSAtgkEFGw7irCYbIRosvkBwnherY/to/ijJSEAopmTz7KdVcg+WJbcGCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59b9dee1ff9159fd31b1f7377b8ab47374573b1503480b7528d03d14ca66f03c","last_reissued_at":"2026-07-05T08:36:44.672645Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:44.672645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aohan Zeng, Bosi Wen, Hongning Wang, Jiale Cheng, Jie Tang, Minlie Huang, Pei Ke, Shengyuan Wang, Xiao Liu, Xuanyu Lei, Yuxiao Dong, Zhuoer Feng","submitted_at":"2023-11-30T16:52:42Z","abstract_excerpt":"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 thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.18702","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2311.18702/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2311.18702","created_at":"2026-07-05T08:36:44.672712+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.18702v2","created_at":"2026-07-05T08:36:44.672712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.18702","created_at":"2026-07-05T08:36:44.672712+00:00"},{"alias_kind":"pith_short_12","alias_value":"LG455YP7SFM7","created_at":"2026-07-05T08:36:44.672712+00:00"},{"alias_kind":"pith_short_16","alias_value":"LG455YP7SFM72MNR","created_at":"2026-07-05T08:36:44.672712+00:00"},{"alias_kind":"pith_short_8","alias_value":"LG455YP7","created_at":"2026-07-05T08:36:44.672712+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22723","citing_title":"BLUEX v2: Benchmarking LLMs on Open-Ended Questions from Brazilian University Entrance Exams","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22723","citing_title":"BLUEX v2: Benchmarking LLMs on Open-Ended Questions from Brazilian University Entrance Exams","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2403.17297","citing_title":"InternLM2 Technical Report","ref_index":176,"is_internal_anchor":false},{"citing_arxiv_id":"2412.21187","citing_title":"Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs","ref_index":117,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23178","citing_title":"Judging the Judges: A Systematic Evaluation of Bias Mitigation Strategies in LLM-as-a-Judge Pipelines","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2502.18864","citing_title":"Towards an AI co-scientist","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LG455YP7SFM72MNR643XXCVUON","json":"https://pith.science/pith/LG455YP7SFM72MNR643XXCVUON.json","graph_json":"https://pith.science/api/pith-number/LG455YP7SFM72MNR643XXCVUON/graph.json","events_json":"https://pith.science/api/pith-number/LG455YP7SFM72MNR643XXCVUON/events.json","paper":"https://pith.science/paper/LG455YP7"},"agent_actions":{"view_html":"https://pith.science/pith/LG455YP7SFM72MNR643XXCVUON","download_json":"https://pith.science/pith/LG455YP7SFM72MNR643XXCVUON.json","view_paper":"https://pith.science/paper/LG455YP7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.18702&json=true","fetch_graph":"https://pith.science/api/pith-number/LG455YP7SFM72MNR643XXCVUON/graph.json","fetch_events":"https://pith.science/api/pith-number/LG455YP7SFM72MNR643XXCVUON/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LG455YP7SFM72MNR643XXCVUON/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LG455YP7SFM72MNR643XXCVUON/action/storage_attestation","attest_author":"https://pith.science/pith/LG455YP7SFM72MNR643XXCVUON/action/author_attestation","sign_citation":"https://pith.science/pith/LG455YP7SFM72MNR643XXCVUON/action/citation_signature","submit_replication":"https://pith.science/pith/LG455YP7SFM72MNR643XXCVUON/action/replication_record"}},"created_at":"2026-07-05T08:36:44.672712+00:00","updated_at":"2026-07-05T08:36:44.672712+00:00"}