{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:E55WZLYPHRO4IOUJFEF43FSX2I","short_pith_number":"pith:E55WZLYP","schema_version":"1.0","canonical_sha256":"277b6caf0f3c5dc43a89290bcd9657d2026163a8f36db7cbcc14a65482514b72","source":{"kind":"arxiv","id":"2506.06539","version":1},"attestation_state":"computed","paper":{"title":"Beyond Facts: Evaluating Intent Hallucination in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haofei Yu, Jiaxuan You, Yijie Hao","submitted_at":"2025-06-06T21:10:55Z","abstract_excerpt":"When exposed to complex queries containing multiple conditions, today's large language models (LLMs) tend to produce responses that only partially satisfy the query while neglecting certain conditions. We therefore introduce the concept of Intent Hallucination. In this phenomenon, LLMs either omit (neglecting to address certain parts) or misinterpret (responding to invented query parts) elements of the given query, leading to intent hallucinated generation. To systematically evaluate intent hallucination, we introduce FAITHQA, a novel benchmark for intent hallucination that contains 20,068 pro"},"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":"2506.06539","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-06T21:10:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"55b0f7e1a274caa7f6e26d95992c7624b9365f36abfc6e90cf3d2b2f711d1477","abstract_canon_sha256":"19686dc55257d890d68916e843764e003280af2f32a5bef3bb8fc123f09ce246"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:51.864016Z","signature_b64":"QTsgyTHXbBOz1+CCB4Db8a+/ohcx0Zm1ZP7h1hpcRv6YS8kj4sP/lP4hjrcTp4TesXR+dZFOHPj6SztX316pBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"277b6caf0f3c5dc43a89290bcd9657d2026163a8f36db7cbcc14a65482514b72","last_reissued_at":"2026-07-05T11:17:51.863602Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:51.863602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Facts: Evaluating Intent Hallucination in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haofei Yu, Jiaxuan You, Yijie Hao","submitted_at":"2025-06-06T21:10:55Z","abstract_excerpt":"When exposed to complex queries containing multiple conditions, today's large language models (LLMs) tend to produce responses that only partially satisfy the query while neglecting certain conditions. We therefore introduce the concept of Intent Hallucination. In this phenomenon, LLMs either omit (neglecting to address certain parts) or misinterpret (responding to invented query parts) elements of the given query, leading to intent hallucinated generation. To systematically evaluate intent hallucination, we introduce FAITHQA, a novel benchmark for intent hallucination that contains 20,068 pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06539","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/2506.06539/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":"2506.06539","created_at":"2026-07-05T11:17:51.863657+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06539v1","created_at":"2026-07-05T11:17:51.863657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06539","created_at":"2026-07-05T11:17:51.863657+00:00"},{"alias_kind":"pith_short_12","alias_value":"E55WZLYPHRO4","created_at":"2026-07-05T11:17:51.863657+00:00"},{"alias_kind":"pith_short_16","alias_value":"E55WZLYPHRO4IOUJ","created_at":"2026-07-05T11:17:51.863657+00:00"},{"alias_kind":"pith_short_8","alias_value":"E55WZLYP","created_at":"2026-07-05T11:17:51.863657+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E55WZLYPHRO4IOUJFEF43FSX2I","json":"https://pith.science/pith/E55WZLYPHRO4IOUJFEF43FSX2I.json","graph_json":"https://pith.science/api/pith-number/E55WZLYPHRO4IOUJFEF43FSX2I/graph.json","events_json":"https://pith.science/api/pith-number/E55WZLYPHRO4IOUJFEF43FSX2I/events.json","paper":"https://pith.science/paper/E55WZLYP"},"agent_actions":{"view_html":"https://pith.science/pith/E55WZLYPHRO4IOUJFEF43FSX2I","download_json":"https://pith.science/pith/E55WZLYPHRO4IOUJFEF43FSX2I.json","view_paper":"https://pith.science/paper/E55WZLYP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06539&json=true","fetch_graph":"https://pith.science/api/pith-number/E55WZLYPHRO4IOUJFEF43FSX2I/graph.json","fetch_events":"https://pith.science/api/pith-number/E55WZLYPHRO4IOUJFEF43FSX2I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E55WZLYPHRO4IOUJFEF43FSX2I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E55WZLYPHRO4IOUJFEF43FSX2I/action/storage_attestation","attest_author":"https://pith.science/pith/E55WZLYPHRO4IOUJFEF43FSX2I/action/author_attestation","sign_citation":"https://pith.science/pith/E55WZLYPHRO4IOUJFEF43FSX2I/action/citation_signature","submit_replication":"https://pith.science/pith/E55WZLYPHRO4IOUJFEF43FSX2I/action/replication_record"}},"created_at":"2026-07-05T11:17:51.863657+00:00","updated_at":"2026-07-05T11:17:51.863657+00:00"}