{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4VO7246OALRVLBJPJFZI4WJXAB","short_pith_number":"pith:4VO7246O","schema_version":"1.0","canonical_sha256":"e55dfd73ce02e355852f49728e5937005c0c28b0aa4dbbd53019b292f93d6935","source":{"kind":"arxiv","id":"2407.17125","version":3},"attestation_state":"computed","paper":{"title":"To Know or Not To Know? Analyzing Self-Consistency of Large Language Models under Ambiguity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anastasiia Sedova, Barbara Plank, Benjamin Roth, Diego Frassinelli, Robert Litschko","submitted_at":"2024-07-24T09:48:48Z","abstract_excerpt":"One of the major aspects contributing to the striking performance of large language models (LLMs) is the vast amount of factual knowledge accumulated during pre-training. Yet, many LLMs suffer from self-inconsistency, which raises doubts about their trustworthiness and reliability. This paper focuses on entity type ambiguity, analyzing the proficiency and consistency of state-of-the-art LLMs in applying factual knowledge when prompted with ambiguous entities. To do so, we propose an evaluation protocol that disentangles knowing from applying knowledge, and test state-of-the-art LLMs on 49 ambi"},"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":"2407.17125","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-24T09:48:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8c970da836cd275b189d29d21ea0857995a82299e87c47be2b1657da48c950fb","abstract_canon_sha256":"18501a9e36e3a1985133a7b9b2a496cc5bb17ce0485ed413bd6806613b7889bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:58.903567Z","signature_b64":"jrOg94Y7o+2Ma+Nufs95vPau8/e6aoOS/jZVcwaxlV4HMy/4ieOQZ97uZeu4Kz+ZJcM7eW2TNeiEvFOBOiVAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e55dfd73ce02e355852f49728e5937005c0c28b0aa4dbbd53019b292f93d6935","last_reissued_at":"2026-07-05T09:15:58.903127Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:58.903127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"To Know or Not To Know? Analyzing Self-Consistency of Large Language Models under Ambiguity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anastasiia Sedova, Barbara Plank, Benjamin Roth, Diego Frassinelli, Robert Litschko","submitted_at":"2024-07-24T09:48:48Z","abstract_excerpt":"One of the major aspects contributing to the striking performance of large language models (LLMs) is the vast amount of factual knowledge accumulated during pre-training. Yet, many LLMs suffer from self-inconsistency, which raises doubts about their trustworthiness and reliability. This paper focuses on entity type ambiguity, analyzing the proficiency and consistency of state-of-the-art LLMs in applying factual knowledge when prompted with ambiguous entities. To do so, we propose an evaluation protocol that disentangles knowing from applying knowledge, and test state-of-the-art LLMs on 49 ambi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17125","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/2407.17125/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":"2407.17125","created_at":"2026-07-05T09:15:58.903187+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.17125v3","created_at":"2026-07-05T09:15:58.903187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17125","created_at":"2026-07-05T09:15:58.903187+00:00"},{"alias_kind":"pith_short_12","alias_value":"4VO7246OALRV","created_at":"2026-07-05T09:15:58.903187+00:00"},{"alias_kind":"pith_short_16","alias_value":"4VO7246OALRVLBJP","created_at":"2026-07-05T09:15:58.903187+00:00"},{"alias_kind":"pith_short_8","alias_value":"4VO7246O","created_at":"2026-07-05T09:15:58.903187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28615","citing_title":"What LLMs explain is not what they believe: Evaluating explanation sufficiency under models' own input beliefs","ref_index":101,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4VO7246OALRVLBJPJFZI4WJXAB","json":"https://pith.science/pith/4VO7246OALRVLBJPJFZI4WJXAB.json","graph_json":"https://pith.science/api/pith-number/4VO7246OALRVLBJPJFZI4WJXAB/graph.json","events_json":"https://pith.science/api/pith-number/4VO7246OALRVLBJPJFZI4WJXAB/events.json","paper":"https://pith.science/paper/4VO7246O"},"agent_actions":{"view_html":"https://pith.science/pith/4VO7246OALRVLBJPJFZI4WJXAB","download_json":"https://pith.science/pith/4VO7246OALRVLBJPJFZI4WJXAB.json","view_paper":"https://pith.science/paper/4VO7246O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.17125&json=true","fetch_graph":"https://pith.science/api/pith-number/4VO7246OALRVLBJPJFZI4WJXAB/graph.json","fetch_events":"https://pith.science/api/pith-number/4VO7246OALRVLBJPJFZI4WJXAB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4VO7246OALRVLBJPJFZI4WJXAB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4VO7246OALRVLBJPJFZI4WJXAB/action/storage_attestation","attest_author":"https://pith.science/pith/4VO7246OALRVLBJPJFZI4WJXAB/action/author_attestation","sign_citation":"https://pith.science/pith/4VO7246OALRVLBJPJFZI4WJXAB/action/citation_signature","submit_replication":"https://pith.science/pith/4VO7246OALRVLBJPJFZI4WJXAB/action/replication_record"}},"created_at":"2026-07-05T09:15:58.903187+00:00","updated_at":"2026-07-05T09:15:58.903187+00:00"}