{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3Q2D2O5EBVXQLNSCXAQUD7OV74","short_pith_number":"pith:3Q2D2O5E","schema_version":"1.0","canonical_sha256":"dc343d3ba40d6f05b642b82141fdd5ff183496bba09e0809ac627bf20a16ff6c","source":{"kind":"arxiv","id":"2410.18359","version":3},"attestation_state":"computed","paper":{"title":"Improving Model Factuality with Fine-grained Critique-based Evaluator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arya Talebzadeh, Carolyn Rose, Daniel Fried, Di Jin, Han Fang, Hejia Zhang, Pradyot Prakash, Quintin Fettes, Sinong Wang, Wenxuan Zhou, Yiqing Xie, Yuning Mao","submitted_at":"2024-10-24T01:41:02Z","abstract_excerpt":"Factuality evaluation aims to detect factual errors produced by language models (LMs) and hence guide the development of more factual models. Towards this goal, we train a factuality evaluator, FenCE, that provides LM generators with claim-level factuality feedback. We conduct data augmentation on a combination of public judgment datasets to train FenCE to (1) generate textual critiques along with scores and (2) make claim-level judgment based on diverse source documents obtained by various tools. We then present a framework that leverages FenCE to improve the factuality of LM generators by co"},"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":"2410.18359","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T01:41:02Z","cross_cats_sorted":[],"title_canon_sha256":"79cb28abb07c450f15945002304a3f67e3a684325cf3c41f0cc22b88cfbe24a3","abstract_canon_sha256":"79a96d4b4c6c5cd0b65d6995221f3c8b1f094216ac0409d355852647baf8b39c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:14.762368Z","signature_b64":"UexOQPhOWM2IKbMxl94j4ekBdTRljjzkdo/X4mGrJxv2p3BewXTqFJcKa7SfYGBlU125spx9LWnkWLz2WeDsCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc343d3ba40d6f05b642b82141fdd5ff183496bba09e0809ac627bf20a16ff6c","last_reissued_at":"2026-07-05T11:13:14.761838Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:14.761838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Model Factuality with Fine-grained Critique-based Evaluator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arya Talebzadeh, Carolyn Rose, Daniel Fried, Di Jin, Han Fang, Hejia Zhang, Pradyot Prakash, Quintin Fettes, Sinong Wang, Wenxuan Zhou, Yiqing Xie, Yuning Mao","submitted_at":"2024-10-24T01:41:02Z","abstract_excerpt":"Factuality evaluation aims to detect factual errors produced by language models (LMs) and hence guide the development of more factual models. Towards this goal, we train a factuality evaluator, FenCE, that provides LM generators with claim-level factuality feedback. We conduct data augmentation on a combination of public judgment datasets to train FenCE to (1) generate textual critiques along with scores and (2) make claim-level judgment based on diverse source documents obtained by various tools. We then present a framework that leverages FenCE to improve the factuality of LM generators by co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18359","kind":"arxiv","version":3},"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/2410.18359/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":"2410.18359","created_at":"2026-07-05T11:13:14.761901+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.18359v3","created_at":"2026-07-05T11:13:14.761901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18359","created_at":"2026-07-05T11:13:14.761901+00:00"},{"alias_kind":"pith_short_12","alias_value":"3Q2D2O5EBVXQ","created_at":"2026-07-05T11:13:14.761901+00:00"},{"alias_kind":"pith_short_16","alias_value":"3Q2D2O5EBVXQLNSC","created_at":"2026-07-05T11:13:14.761901+00:00"},{"alias_kind":"pith_short_8","alias_value":"3Q2D2O5E","created_at":"2026-07-05T11:13:14.761901+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.15594","citing_title":"A Survey on LLM-as-a-Judge","ref_index":179,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05579","citing_title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","ref_index":261,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3Q2D2O5EBVXQLNSCXAQUD7OV74","json":"https://pith.science/pith/3Q2D2O5EBVXQLNSCXAQUD7OV74.json","graph_json":"https://pith.science/api/pith-number/3Q2D2O5EBVXQLNSCXAQUD7OV74/graph.json","events_json":"https://pith.science/api/pith-number/3Q2D2O5EBVXQLNSCXAQUD7OV74/events.json","paper":"https://pith.science/paper/3Q2D2O5E"},"agent_actions":{"view_html":"https://pith.science/pith/3Q2D2O5EBVXQLNSCXAQUD7OV74","download_json":"https://pith.science/pith/3Q2D2O5EBVXQLNSCXAQUD7OV74.json","view_paper":"https://pith.science/paper/3Q2D2O5E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.18359&json=true","fetch_graph":"https://pith.science/api/pith-number/3Q2D2O5EBVXQLNSCXAQUD7OV74/graph.json","fetch_events":"https://pith.science/api/pith-number/3Q2D2O5EBVXQLNSCXAQUD7OV74/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3Q2D2O5EBVXQLNSCXAQUD7OV74/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3Q2D2O5EBVXQLNSCXAQUD7OV74/action/storage_attestation","attest_author":"https://pith.science/pith/3Q2D2O5EBVXQLNSCXAQUD7OV74/action/author_attestation","sign_citation":"https://pith.science/pith/3Q2D2O5EBVXQLNSCXAQUD7OV74/action/citation_signature","submit_replication":"https://pith.science/pith/3Q2D2O5EBVXQLNSCXAQUD7OV74/action/replication_record"}},"created_at":"2026-07-05T11:13:14.761901+00:00","updated_at":"2026-07-05T11:13:14.761901+00:00"}