{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JQRCIHE4MOGFAA4DISVHHOJJHE","short_pith_number":"pith:JQRCIHE4","schema_version":"1.0","canonical_sha256":"4c22241c9c638c50038344aa73b9293929474826c6b17177ec7ace07d7db1cc3","source":{"kind":"arxiv","id":"2401.06855","version":4},"attestation_state":"computed","paper":{"title":"Fine-grained Hallucination Detection and Editing for Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhika Mishra, Akari Asai, Graham Neubig, Hannaneh Hajishirzi, Vidhisha Balachandran, Yizhong Wang, Yulia Tsvetkov","submitted_at":"2024-01-12T19:02:48Z","abstract_excerpt":"Large language models (LMs) are prone to generate factual errors, which are often called hallucinations. In this paper, we introduce a comprehensive taxonomy of hallucinations and argue that hallucinations manifest in diverse forms, each requiring varying degrees of careful assessments to verify factuality. We propose a novel task of automatic fine-grained hallucination detection and construct a new evaluation benchmark, FavaBench, that includes about one thousand fine-grained human judgments on three LM outputs across various domains. Our analysis reveals that ChatGPT and Llama2-Chat (70B, 7B"},"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":"2401.06855","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T19:02:48Z","cross_cats_sorted":[],"title_canon_sha256":"3c627c04fae7b710c767033a2472e9f4d77bfa55df4079e7950c90f3f232eecd","abstract_canon_sha256":"839e083fba7ccd5f16118a580155f638b5908f68482b153237458501d1aa3619"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:46.076649Z","signature_b64":"1R+pDHMEuBEEiCilY5hJFWj80Bvmn7UcC9d6+WOgHevBwY4686waAVTYvRjk5Gh+fPbYMXMGyzevGskZ0NAoBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c22241c9c638c50038344aa73b9293929474826c6b17177ec7ace07d7db1cc3","last_reissued_at":"2026-07-05T08:54:46.076275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:46.076275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-grained Hallucination Detection and Editing for Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhika Mishra, Akari Asai, Graham Neubig, Hannaneh Hajishirzi, Vidhisha Balachandran, Yizhong Wang, Yulia Tsvetkov","submitted_at":"2024-01-12T19:02:48Z","abstract_excerpt":"Large language models (LMs) are prone to generate factual errors, which are often called hallucinations. In this paper, we introduce a comprehensive taxonomy of hallucinations and argue that hallucinations manifest in diverse forms, each requiring varying degrees of careful assessments to verify factuality. We propose a novel task of automatic fine-grained hallucination detection and construct a new evaluation benchmark, FavaBench, that includes about one thousand fine-grained human judgments on three LM outputs across various domains. Our analysis reveals that ChatGPT and Llama2-Chat (70B, 7B"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06855","kind":"arxiv","version":4},"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/2401.06855/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":"2401.06855","created_at":"2026-07-05T08:54:46.076339+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.06855v4","created_at":"2026-07-05T08:54:46.076339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06855","created_at":"2026-07-05T08:54:46.076339+00:00"},{"alias_kind":"pith_short_12","alias_value":"JQRCIHE4MOGF","created_at":"2026-07-05T08:54:46.076339+00:00"},{"alias_kind":"pith_short_16","alias_value":"JQRCIHE4MOGFAA4D","created_at":"2026-07-05T08:54:46.076339+00:00"},{"alias_kind":"pith_short_8","alias_value":"JQRCIHE4","created_at":"2026-07-05T08:54:46.076339+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05721","citing_title":"SpanUQ: Span-Level Uncertainty Quantification for Large Language Model Generation","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21517","citing_title":"MedHal-Loc: Are \"Explainable-by-Architecture\" Medical Hallucination Detectors Faithful Localizers? A Localization Benchmark","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08605","citing_title":"Multilingual Fact-Checking at Scale: Fine-Tuned Compact Models vs LLMs","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24919","citing_title":"MultiHaluDet: Multilingual Hallucination Detection via LLM Hidden State Probing","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28264","citing_title":"Entropy Distribution as a Fingerprint for Hallucinations in Generative Models","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29523","citing_title":"K-FinHallu: A Hallucination Detection Benchmark for Multi-Turn RAG in Korean Finance","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29826","citing_title":"Towards Localized and Disentangled Knowledge Editing for Multimodal Large Language Models","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02443","citing_title":"HalluScan: A Systematic Benchmark for Detecting and Mitigating Hallucinations in Instruction-Following LLMs","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2509.25868","citing_title":"ReFACT: A Benchmark for Scientific Confabulation Detection with Positional Error Annotations","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06714","citing_title":"Steering the Verifiability of Multimodal AI Hallucinations","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02443","citing_title":"HalluScan: A Systematic Benchmark for Detecting and Mitigating Hallucinations in Instruction-Following LLMs","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JQRCIHE4MOGFAA4DISVHHOJJHE","json":"https://pith.science/pith/JQRCIHE4MOGFAA4DISVHHOJJHE.json","graph_json":"https://pith.science/api/pith-number/JQRCIHE4MOGFAA4DISVHHOJJHE/graph.json","events_json":"https://pith.science/api/pith-number/JQRCIHE4MOGFAA4DISVHHOJJHE/events.json","paper":"https://pith.science/paper/JQRCIHE4"},"agent_actions":{"view_html":"https://pith.science/pith/JQRCIHE4MOGFAA4DISVHHOJJHE","download_json":"https://pith.science/pith/JQRCIHE4MOGFAA4DISVHHOJJHE.json","view_paper":"https://pith.science/paper/JQRCIHE4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.06855&json=true","fetch_graph":"https://pith.science/api/pith-number/JQRCIHE4MOGFAA4DISVHHOJJHE/graph.json","fetch_events":"https://pith.science/api/pith-number/JQRCIHE4MOGFAA4DISVHHOJJHE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JQRCIHE4MOGFAA4DISVHHOJJHE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JQRCIHE4MOGFAA4DISVHHOJJHE/action/storage_attestation","attest_author":"https://pith.science/pith/JQRCIHE4MOGFAA4DISVHHOJJHE/action/author_attestation","sign_citation":"https://pith.science/pith/JQRCIHE4MOGFAA4DISVHHOJJHE/action/citation_signature","submit_replication":"https://pith.science/pith/JQRCIHE4MOGFAA4DISVHHOJJHE/action/replication_record"}},"created_at":"2026-07-05T08:54:46.076339+00:00","updated_at":"2026-07-05T08:54:46.076339+00:00"}