{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LG455YP7SFM72MNR643XXCVUON","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6aa0b4ead29ecf82781ebae19cd6e5ebbc2fd0a5de755446b113c6cfd660c113","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-30T16:52:42Z","title_canon_sha256":"d2820354a47908b08163eeded4a1a8d40018d93ca10cb17cb6ba66e52561eda5"},"schema_version":"1.0","source":{"id":"2311.18702","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.18702","created_at":"2026-07-05T08:36:44Z"},{"alias_kind":"arxiv_version","alias_value":"2311.18702v2","created_at":"2026-07-05T08:36:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.18702","created_at":"2026-07-05T08:36:44Z"},{"alias_kind":"pith_short_12","alias_value":"LG455YP7SFM7","created_at":"2026-07-05T08:36:44Z"},{"alias_kind":"pith_short_16","alias_value":"LG455YP7SFM72MNR","created_at":"2026-07-05T08:36:44Z"},{"alias_kind":"pith_short_8","alias_value":"LG455YP7","created_at":"2026-07-05T08:36:44Z"}],"graph_snapshots":[{"event_id":"sha256:d00867f934726302987455e782ff61552ba3f2194cc8bd31f61b3295cb6d7931","target":"graph","created_at":"2026-07-05T08:36:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2311.18702/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-30T16:52:42Z","title":"CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.18702","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bf4bb44a25eca2e9f1d3aa50c45ac69055ee327989776556f73b027bf6ca479d","target":"record","created_at":"2026-07-05T08:36:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6aa0b4ead29ecf82781ebae19cd6e5ebbc2fd0a5de755446b113c6cfd660c113","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-30T16:52:42Z","title_canon_sha256":"d2820354a47908b08163eeded4a1a8d40018d93ca10cb17cb6ba66e52561eda5"},"schema_version":"1.0","source":{"id":"2311.18702","kind":"arxiv","version":2}},"canonical_sha256":"59b9dee1ff9159fd31b1f7377b8ab47374573b1503480b7528d03d14ca66f03c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59b9dee1ff9159fd31b1f7377b8ab47374573b1503480b7528d03d14ca66f03c","first_computed_at":"2026-07-05T08:36:44.672645Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:44.672645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3/x6SFrLjKEbSVAn7BeZTC0tcwfNiSAtgkEFGw7irCYbIRosvkBwnherY/to/ijJSEAopmTz7KdVcg+WJbcGCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:44.673218Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.18702","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf4bb44a25eca2e9f1d3aa50c45ac69055ee327989776556f73b027bf6ca479d","sha256:d00867f934726302987455e782ff61552ba3f2194cc8bd31f61b3295cb6d7931"],"state_sha256":"f7a5111c5a60c22daa5fd364ab21cebc0642a4bcc59367cfbff8ca0b39badca9"}