{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SCWAAG7RIS6VBR35YM46KUKFU3","short_pith_number":"pith:SCWAAG7R","schema_version":"1.0","canonical_sha256":"90ac001bf144bd50c77dc339e55145a6f31ff44b4f45fda43f635c27966055b4","source":{"kind":"arxiv","id":"2406.13929","version":1},"attestation_state":"computed","paper":{"title":"Large Language Models are Skeptics: False Negative Problem of Input-conflicting Hallucination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jongyoon Song, Sangwon Yu, Sungroh Yoon","submitted_at":"2024-06-20T01:53:25Z","abstract_excerpt":"In this paper, we identify a new category of bias that induces input-conflicting hallucinations, where large language models (LLMs) generate responses inconsistent with the content of the input context. This issue we have termed the false negative problem refers to the phenomenon where LLMs are predisposed to return negative judgments when assessing the correctness of a statement given the context. In experiments involving pairs of statements that contain the same information but have contradictory factual directions, we observe that LLMs exhibit a bias toward false negatives. Specifically, th"},"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":"2406.13929","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-20T01:53:25Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fc9497445948a99b0621f30deb320e7ec8874a641dd5303703e60453d57ce6ac","abstract_canon_sha256":"f206df0e236deed21d0b59c47e6c2c73f61d8594d25b47a3c16147b4166c1bc8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:36.547483Z","signature_b64":"YDkv6FK4K2yCwH8wcM+wQgFfdvzkQrgcC4MHwiZ1Z9jvAAGHIq1UysDzXZEo2JptP+XffSZa8eh22MfEUp8sAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90ac001bf144bd50c77dc339e55145a6f31ff44b4f45fda43f635c27966055b4","last_reissued_at":"2026-07-05T08:34:36.547084Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:36.547084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models are Skeptics: False Negative Problem of Input-conflicting Hallucination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jongyoon Song, Sangwon Yu, Sungroh Yoon","submitted_at":"2024-06-20T01:53:25Z","abstract_excerpt":"In this paper, we identify a new category of bias that induces input-conflicting hallucinations, where large language models (LLMs) generate responses inconsistent with the content of the input context. This issue we have termed the false negative problem refers to the phenomenon where LLMs are predisposed to return negative judgments when assessing the correctness of a statement given the context. In experiments involving pairs of statements that contain the same information but have contradictory factual directions, we observe that LLMs exhibit a bias toward false negatives. Specifically, th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13929","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/2406.13929/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":"2406.13929","created_at":"2026-07-05T08:34:36.547137+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13929v1","created_at":"2026-07-05T08:34:36.547137+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13929","created_at":"2026-07-05T08:34:36.547137+00:00"},{"alias_kind":"pith_short_12","alias_value":"SCWAAG7RIS6V","created_at":"2026-07-05T08:34:36.547137+00:00"},{"alias_kind":"pith_short_16","alias_value":"SCWAAG7RIS6VBR35","created_at":"2026-07-05T08:34:36.547137+00:00"},{"alias_kind":"pith_short_8","alias_value":"SCWAAG7R","created_at":"2026-07-05T08:34:36.547137+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/SCWAAG7RIS6VBR35YM46KUKFU3","json":"https://pith.science/pith/SCWAAG7RIS6VBR35YM46KUKFU3.json","graph_json":"https://pith.science/api/pith-number/SCWAAG7RIS6VBR35YM46KUKFU3/graph.json","events_json":"https://pith.science/api/pith-number/SCWAAG7RIS6VBR35YM46KUKFU3/events.json","paper":"https://pith.science/paper/SCWAAG7R"},"agent_actions":{"view_html":"https://pith.science/pith/SCWAAG7RIS6VBR35YM46KUKFU3","download_json":"https://pith.science/pith/SCWAAG7RIS6VBR35YM46KUKFU3.json","view_paper":"https://pith.science/paper/SCWAAG7R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13929&json=true","fetch_graph":"https://pith.science/api/pith-number/SCWAAG7RIS6VBR35YM46KUKFU3/graph.json","fetch_events":"https://pith.science/api/pith-number/SCWAAG7RIS6VBR35YM46KUKFU3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SCWAAG7RIS6VBR35YM46KUKFU3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SCWAAG7RIS6VBR35YM46KUKFU3/action/storage_attestation","attest_author":"https://pith.science/pith/SCWAAG7RIS6VBR35YM46KUKFU3/action/author_attestation","sign_citation":"https://pith.science/pith/SCWAAG7RIS6VBR35YM46KUKFU3/action/citation_signature","submit_replication":"https://pith.science/pith/SCWAAG7RIS6VBR35YM46KUKFU3/action/replication_record"}},"created_at":"2026-07-05T08:34:36.547137+00:00","updated_at":"2026-07-05T08:34:36.547137+00:00"}