{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HAMR7AM3OU3LSTZBHTAXSNQRSQ","short_pith_number":"pith:HAMR7AM3","schema_version":"1.0","canonical_sha256":"38191f819b7536b94f213cc1793611942372268cbd5d62efdd9c10d4789eea10","source":{"kind":"arxiv","id":"2305.15852","version":3},"attestation_state":"computed","paper":{"title":"Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jingxuan He, Martin Vechev, Niels M\\\"undler, Slobodan Jenko","submitted_at":"2023-05-25T08:43:46Z","abstract_excerpt":"Large language models (large LMs) are susceptible to producing text that contains hallucinated content. An important instance of this problem is self-contradiction, where the LM generates two contradictory sentences within the same context. In this work, we present a comprehensive investigation into self-contradiction for various instruction-tuned LMs, covering evaluation, detection, and mitigation. Our primary evaluation task is open-domain text generation, but we also demonstrate the applicability of our approach to shorter question answering. Our analysis reveals the prevalence of self-cont"},"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":"2305.15852","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-25T08:43:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"34b605e23c0ccae2ec037b258b586bfcfffd8c3e9a3e6f992b6322896423872d","abstract_canon_sha256":"9ddfd395bc04d01a34910a93a9a510be12c7f869972b0ce70aac0886cffbff4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:48.726835Z","signature_b64":"XD2l5HQXUBOF+/sAKzFx5120fHzp4ckym1xUk1GlTgn/CmJtFzEYA9sAb7R3eqTpwhPsssvyH9zqEVL22MGBDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38191f819b7536b94f213cc1793611942372268cbd5d62efdd9c10d4789eea10","last_reissued_at":"2026-07-05T07:56:48.726188Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:48.726188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jingxuan He, Martin Vechev, Niels M\\\"undler, Slobodan Jenko","submitted_at":"2023-05-25T08:43:46Z","abstract_excerpt":"Large language models (large LMs) are susceptible to producing text that contains hallucinated content. An important instance of this problem is self-contradiction, where the LM generates two contradictory sentences within the same context. In this work, we present a comprehensive investigation into self-contradiction for various instruction-tuned LMs, covering evaluation, detection, and mitigation. Our primary evaluation task is open-domain text generation, but we also demonstrate the applicability of our approach to shorter question answering. Our analysis reveals the prevalence of self-cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15852","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/2305.15852/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":"2305.15852","created_at":"2026-07-05T07:56:48.726271+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.15852v3","created_at":"2026-07-05T07:56:48.726271+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15852","created_at":"2026-07-05T07:56:48.726271+00:00"},{"alias_kind":"pith_short_12","alias_value":"HAMR7AM3OU3L","created_at":"2026-07-05T07:56:48.726271+00:00"},{"alias_kind":"pith_short_16","alias_value":"HAMR7AM3OU3LSTZB","created_at":"2026-07-05T07:56:48.726271+00:00"},{"alias_kind":"pith_short_8","alias_value":"HAMR7AM3","created_at":"2026-07-05T07:56:48.726271+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01441","citing_title":"Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM Prompts","ref_index":21,"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":39,"is_internal_anchor":false},{"citing_arxiv_id":"2507.20546","citing_title":"Enhancing Hallucination Detection via Future Context","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2406.15927","citing_title":"Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2309.05922","citing_title":"A Survey of Hallucination in Large Foundation Models","ref_index":138,"is_internal_anchor":false},{"citing_arxiv_id":"2309.03883","citing_title":"DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2401.01313","citing_title":"A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17284","citing_title":"HalluClear: Diagnosing, Evaluating and Mitigating Hallucinations in GUI Agents","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HAMR7AM3OU3LSTZBHTAXSNQRSQ","json":"https://pith.science/pith/HAMR7AM3OU3LSTZBHTAXSNQRSQ.json","graph_json":"https://pith.science/api/pith-number/HAMR7AM3OU3LSTZBHTAXSNQRSQ/graph.json","events_json":"https://pith.science/api/pith-number/HAMR7AM3OU3LSTZBHTAXSNQRSQ/events.json","paper":"https://pith.science/paper/HAMR7AM3"},"agent_actions":{"view_html":"https://pith.science/pith/HAMR7AM3OU3LSTZBHTAXSNQRSQ","download_json":"https://pith.science/pith/HAMR7AM3OU3LSTZBHTAXSNQRSQ.json","view_paper":"https://pith.science/paper/HAMR7AM3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.15852&json=true","fetch_graph":"https://pith.science/api/pith-number/HAMR7AM3OU3LSTZBHTAXSNQRSQ/graph.json","fetch_events":"https://pith.science/api/pith-number/HAMR7AM3OU3LSTZBHTAXSNQRSQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HAMR7AM3OU3LSTZBHTAXSNQRSQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HAMR7AM3OU3LSTZBHTAXSNQRSQ/action/storage_attestation","attest_author":"https://pith.science/pith/HAMR7AM3OU3LSTZBHTAXSNQRSQ/action/author_attestation","sign_citation":"https://pith.science/pith/HAMR7AM3OU3LSTZBHTAXSNQRSQ/action/citation_signature","submit_replication":"https://pith.science/pith/HAMR7AM3OU3LSTZBHTAXSNQRSQ/action/replication_record"}},"created_at":"2026-07-05T07:56:48.726271+00:00","updated_at":"2026-07-05T07:56:48.726271+00:00"}