{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:C3L4IUNEDKHJ73CTRC7VMPTCJC","short_pith_number":"pith:C3L4IUNE","schema_version":"1.0","canonical_sha256":"16d7c451a41a8e9fec5388bf563e6248872541830cb54cafb9d56c76f55a57ae","source":{"kind":"arxiv","id":"2405.14486","version":1},"attestation_state":"computed","paper":{"title":"RefChecker: Reference-based Fine-grained Hallucination Checker and Benchmark for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dongyu Ru, Lin Qiu, Pengfei Liu, Qipeng Guo, Tianhang Zhang, Xiangkun Hu, Yang Xu, Yue Zhang, Yun Luo, Zheng Zhang","submitted_at":"2024-05-23T12:18:11Z","abstract_excerpt":"Large Language Models (LLMs) have shown impressive capabilities but also a concerning tendency to hallucinate. This paper presents RefChecker, a framework that introduces claim-triplets to represent claims in LLM responses, aiming to detect fine-grained hallucinations. In RefChecker, an extractor generates claim-triplets from a response, which are then evaluated by a checker against a reference. We delineate three task settings: Zero, Noisy and Accurate Context, to reflect various real-world use cases. We curated a benchmark spanning various NLP tasks and annotated 11k claim-triplets from 2.1k"},"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":"2405.14486","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-23T12:18:11Z","cross_cats_sorted":[],"title_canon_sha256":"b19feab0ee563c7807e5c617074d2b4de33998f307a554c3351c3baf6a621226","abstract_canon_sha256":"88bfd1b4867ce515a79e9ad0b0f179e04326bc5f01d179a05e3c37b3bfa6a5aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:24.363540Z","signature_b64":"yCEcXAF/jlj2oQ2aByVW1xjXzyJRUR19KUJrEftzBiBW+Qv65VfkMuosdF22YHAAyqrkK22Hc3/HPqX9UkbGCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16d7c451a41a8e9fec5388bf563e6248872541830cb54cafb9d56c76f55a57ae","last_reissued_at":"2026-07-05T08:22:24.362990Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:24.362990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RefChecker: Reference-based Fine-grained Hallucination Checker and Benchmark for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dongyu Ru, Lin Qiu, Pengfei Liu, Qipeng Guo, Tianhang Zhang, Xiangkun Hu, Yang Xu, Yue Zhang, Yun Luo, Zheng Zhang","submitted_at":"2024-05-23T12:18:11Z","abstract_excerpt":"Large Language Models (LLMs) have shown impressive capabilities but also a concerning tendency to hallucinate. This paper presents RefChecker, a framework that introduces claim-triplets to represent claims in LLM responses, aiming to detect fine-grained hallucinations. In RefChecker, an extractor generates claim-triplets from a response, which are then evaluated by a checker against a reference. We delineate three task settings: Zero, Noisy and Accurate Context, to reflect various real-world use cases. We curated a benchmark spanning various NLP tasks and annotated 11k claim-triplets from 2.1k"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14486","kind":"arxiv","version":1},"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/2405.14486/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":"2405.14486","created_at":"2026-07-05T08:22:24.363065+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.14486v1","created_at":"2026-07-05T08:22:24.363065+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14486","created_at":"2026-07-05T08:22:24.363065+00:00"},{"alias_kind":"pith_short_12","alias_value":"C3L4IUNEDKHJ","created_at":"2026-07-05T08:22:24.363065+00:00"},{"alias_kind":"pith_short_16","alias_value":"C3L4IUNEDKHJ73CT","created_at":"2026-07-05T08:22:24.363065+00:00"},{"alias_kind":"pith_short_8","alias_value":"C3L4IUNE","created_at":"2026-07-05T08:22:24.363065+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21071","citing_title":"Fine-grained Claim-level RAG Benchmark for Law","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22963","citing_title":"Graph Alignment Topology as an Inductive Bias for Grounding Detection","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21071","citing_title":"Fine-grained Claim-level RAG Benchmark for Law","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21071","citing_title":"Fine-grained Claim-level RAG Benchmark for Law","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2512.07515","citing_title":"TPA: Next Token Probability Attribution for Detecting Hallucinations in RAG","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05348","citing_title":"From Retinal Evidence to Safe Decisions: RETINA-SAFE and ECRT for Hallucination Risk Triage in Medical LLMs","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C3L4IUNEDKHJ73CTRC7VMPTCJC","json":"https://pith.science/pith/C3L4IUNEDKHJ73CTRC7VMPTCJC.json","graph_json":"https://pith.science/api/pith-number/C3L4IUNEDKHJ73CTRC7VMPTCJC/graph.json","events_json":"https://pith.science/api/pith-number/C3L4IUNEDKHJ73CTRC7VMPTCJC/events.json","paper":"https://pith.science/paper/C3L4IUNE"},"agent_actions":{"view_html":"https://pith.science/pith/C3L4IUNEDKHJ73CTRC7VMPTCJC","download_json":"https://pith.science/pith/C3L4IUNEDKHJ73CTRC7VMPTCJC.json","view_paper":"https://pith.science/paper/C3L4IUNE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.14486&json=true","fetch_graph":"https://pith.science/api/pith-number/C3L4IUNEDKHJ73CTRC7VMPTCJC/graph.json","fetch_events":"https://pith.science/api/pith-number/C3L4IUNEDKHJ73CTRC7VMPTCJC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C3L4IUNEDKHJ73CTRC7VMPTCJC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C3L4IUNEDKHJ73CTRC7VMPTCJC/action/storage_attestation","attest_author":"https://pith.science/pith/C3L4IUNEDKHJ73CTRC7VMPTCJC/action/author_attestation","sign_citation":"https://pith.science/pith/C3L4IUNEDKHJ73CTRC7VMPTCJC/action/citation_signature","submit_replication":"https://pith.science/pith/C3L4IUNEDKHJ73CTRC7VMPTCJC/action/replication_record"}},"created_at":"2026-07-05T08:22:24.363065+00:00","updated_at":"2026-07-05T08:22:24.363065+00:00"}