{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FHVBIEZQM6STQO7KATAF5PWMHJ","short_pith_number":"pith:FHVBIEZQ","schema_version":"1.0","canonical_sha256":"29ea14133067a5383bea04c05ebecc3a403010654d5b18d13ce7ab8ffefe36b3","source":{"kind":"arxiv","id":"2504.17550","version":1},"attestation_state":"computed","paper":{"title":"HalluLens: LLM Hallucination Benchmark","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alan Schelten, Anthony Hartshorn, Cheng Zhang, Nicola Cancedda, Pascale Fung, Tara Fowler, Yejin Bang, Ziwei Ji","submitted_at":"2025-04-24T13:40:27Z","abstract_excerpt":"Large language models (LLMs) often generate responses that deviate from user input or training data, a phenomenon known as \"hallucination.\" These hallucinations undermine user trust and hinder the adoption of generative AI systems. Addressing hallucinations is essential for the advancement of LLMs. This paper introduces a comprehensive hallucination benchmark, incorporating both new extrinsic and existing intrinsic evaluation tasks, built upon clear taxonomy of hallucination. A major challenge in benchmarking hallucinations is the lack of a unified framework due to inconsistent definitions and"},"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":"2504.17550","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-24T13:40:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4887496cc92eb8b19aa488da5d2728ced47bd0c69fde59930ca40709d78e3f48","abstract_canon_sha256":"501c5241f56b1498ea17fe4c4bc44d302a54c85526b13ae54e44c10dcdabd999"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:30.746867Z","signature_b64":"9iYgnbF8ojn22TJDz+Mhp7YhIC8/O0Jqty7PrxuJsXNoglUkEXg1z8tGteeDfp2smRW5kv21GjWuxn7st8MvBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29ea14133067a5383bea04c05ebecc3a403010654d5b18d13ce7ab8ffefe36b3","last_reissued_at":"2026-07-05T10:53:30.746275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:30.746275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HalluLens: LLM Hallucination Benchmark","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alan Schelten, Anthony Hartshorn, Cheng Zhang, Nicola Cancedda, Pascale Fung, Tara Fowler, Yejin Bang, Ziwei Ji","submitted_at":"2025-04-24T13:40:27Z","abstract_excerpt":"Large language models (LLMs) often generate responses that deviate from user input or training data, a phenomenon known as \"hallucination.\" These hallucinations undermine user trust and hinder the adoption of generative AI systems. Addressing hallucinations is essential for the advancement of LLMs. This paper introduces a comprehensive hallucination benchmark, incorporating both new extrinsic and existing intrinsic evaluation tasks, built upon clear taxonomy of hallucination. A major challenge in benchmarking hallucinations is the lack of a unified framework due to inconsistent definitions and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17550","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/2504.17550/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":"2504.17550","created_at":"2026-07-05T10:53:30.746343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.17550v1","created_at":"2026-07-05T10:53:30.746343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17550","created_at":"2026-07-05T10:53:30.746343+00:00"},{"alias_kind":"pith_short_12","alias_value":"FHVBIEZQM6ST","created_at":"2026-07-05T10:53:30.746343+00:00"},{"alias_kind":"pith_short_16","alias_value":"FHVBIEZQM6STQO7K","created_at":"2026-07-05T10:53:30.746343+00:00"},{"alias_kind":"pith_short_8","alias_value":"FHVBIEZQ","created_at":"2026-07-05T10:53:30.746343+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03142","citing_title":"Disentangling Visual and Factual Correctness in LVLMs' Visualization Literacy","ref_index":41,"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":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30018","citing_title":"Latent Performance Profiling of Large Language Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06674","citing_title":"What Do People Actually Want From AI? Mapping Preference Plurality","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20591","citing_title":"Do No Harm? Hallucination and Actor-Level Abuse in Web-Deployed Medical Large Language Models","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2509.25868","citing_title":"ReFACT: A Benchmark for Scientific Confabulation Detection with Positional Error Annotations","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12813","citing_title":"REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations","ref_index":105,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10442","citing_title":"StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10442","citing_title":"StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24665","citing_title":"Benchmarking Source-Sensitive Reasoning in Turkish: Humans and LLMs under Evidential Trust Manipulation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05953","citing_title":"Hallucination as an Anomaly: Dynamic Intervention via Probabilistic Circuits","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08082","citing_title":"From Binary Groundedness to Support Relations: Towards a Reader-Centred Taxonomy for Comprehension of AI Output","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17761","citing_title":"Contrastive Attribution in the Wild: An Interpretability Analysis of LLM Failures on Realistic Benchmarks","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17284","citing_title":"HalluClear: Diagnosing, Evaluating and Mitigating Hallucinations in GUI Agents","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FHVBIEZQM6STQO7KATAF5PWMHJ","json":"https://pith.science/pith/FHVBIEZQM6STQO7KATAF5PWMHJ.json","graph_json":"https://pith.science/api/pith-number/FHVBIEZQM6STQO7KATAF5PWMHJ/graph.json","events_json":"https://pith.science/api/pith-number/FHVBIEZQM6STQO7KATAF5PWMHJ/events.json","paper":"https://pith.science/paper/FHVBIEZQ"},"agent_actions":{"view_html":"https://pith.science/pith/FHVBIEZQM6STQO7KATAF5PWMHJ","download_json":"https://pith.science/pith/FHVBIEZQM6STQO7KATAF5PWMHJ.json","view_paper":"https://pith.science/paper/FHVBIEZQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.17550&json=true","fetch_graph":"https://pith.science/api/pith-number/FHVBIEZQM6STQO7KATAF5PWMHJ/graph.json","fetch_events":"https://pith.science/api/pith-number/FHVBIEZQM6STQO7KATAF5PWMHJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FHVBIEZQM6STQO7KATAF5PWMHJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FHVBIEZQM6STQO7KATAF5PWMHJ/action/storage_attestation","attest_author":"https://pith.science/pith/FHVBIEZQM6STQO7KATAF5PWMHJ/action/author_attestation","sign_citation":"https://pith.science/pith/FHVBIEZQM6STQO7KATAF5PWMHJ/action/citation_signature","submit_replication":"https://pith.science/pith/FHVBIEZQM6STQO7KATAF5PWMHJ/action/replication_record"}},"created_at":"2026-07-05T10:53:30.746343+00:00","updated_at":"2026-07-05T10:53:30.746343+00:00"}