{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2KQVCP643X7UESPS4O7MNJDIRW","short_pith_number":"pith:2KQVCP64","schema_version":"1.0","canonical_sha256":"d2a1513fdcddff4249f2e3bec6a4688dac4ed39da7526e1e50e45c7fb1191328","source":{"kind":"arxiv","id":"2305.18153","version":2},"attestation_state":"computed","paper":{"title":"Do Large Language Models Know What They Don't Know?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiawen Wu, Qipeng Guo, Qiushi Sun, Xipeng Qiu, Xuanjing Huang, Zhangyue Yin","submitted_at":"2023-05-29T15:30:13Z","abstract_excerpt":"Large language models (LLMs) have a wealth of knowledge that allows them to excel in various Natural Language Processing (NLP) tasks. Current research focuses on enhancing their performance within their existing knowledge. Despite their vast knowledge, LLMs are still limited by the amount of information they can accommodate and comprehend. Therefore, the ability to understand their own limitations on the unknows, referred to as self-knowledge, is of paramount importance. This study aims to evaluate LLMs' self-knowledge by assessing their ability to identify unanswerable or unknowable questions"},"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":"2305.18153","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-29T15:30:13Z","cross_cats_sorted":[],"title_canon_sha256":"b37aad5e4e6d73908c272ffe4060566dad44bba6369f8050ba60fd0d6e1607d3","abstract_canon_sha256":"66bda1225d95c2ff4c66a92bc4406ef57b08f829fb9c858d32664e7ea6a23db3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:33.265688Z","signature_b64":"oSICq9266JB0cm2r08MPCpFhdXlZG3yqn9wtylNouYaaf4SyQCMH3HP8hYWk/MH/05laD/I5A7Shk5XWSAc9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2a1513fdcddff4249f2e3bec6a4688dac4ed39da7526e1e50e45c7fb1191328","last_reissued_at":"2026-07-05T06:15:33.265149Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:33.265149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do Large Language Models Know What They Don't Know?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiawen Wu, Qipeng Guo, Qiushi Sun, Xipeng Qiu, Xuanjing Huang, Zhangyue Yin","submitted_at":"2023-05-29T15:30:13Z","abstract_excerpt":"Large language models (LLMs) have a wealth of knowledge that allows them to excel in various Natural Language Processing (NLP) tasks. Current research focuses on enhancing their performance within their existing knowledge. Despite their vast knowledge, LLMs are still limited by the amount of information they can accommodate and comprehend. Therefore, the ability to understand their own limitations on the unknows, referred to as self-knowledge, is of paramount importance. This study aims to evaluate LLMs' self-knowledge by assessing their ability to identify unanswerable or unknowable questions"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18153","kind":"arxiv","version":2},"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/2305.18153/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":"2305.18153","created_at":"2026-07-05T06:15:33.265219+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18153v2","created_at":"2026-07-05T06:15:33.265219+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18153","created_at":"2026-07-05T06:15:33.265219+00:00"},{"alias_kind":"pith_short_12","alias_value":"2KQVCP643X7U","created_at":"2026-07-05T06:15:33.265219+00:00"},{"alias_kind":"pith_short_16","alias_value":"2KQVCP643X7UESPS","created_at":"2026-07-05T06:15:33.265219+00:00"},{"alias_kind":"pith_short_8","alias_value":"2KQVCP64","created_at":"2026-07-05T06:15:33.265219+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":234,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03535","citing_title":"Can LLM Rerankers Predict Their Own Ranking Performance?","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":233,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23952","citing_title":"Machine Psychometrics: A Mathematical Psychology of Artificial Intelligence","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21652","citing_title":"Look-Closer-Then-Diagnose: Confidence-Aware Ultrasound VQA via Active Zooming","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29184","citing_title":"BaRA: Bayesian Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2404.13076","citing_title":"LLM Evaluators Recognize and Favor Their Own Generations","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21652","citing_title":"Look-Closer-Then-Diagnose: Confidence-Aware Ultrasound VQA via Active Zooming","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17324","citing_title":"ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents","ref_index":108,"is_internal_anchor":false},{"citing_arxiv_id":"2401.05561","citing_title":"TrustLLM: Trustworthiness in Large Language Models","ref_index":222,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10718","citing_title":"SciPredict: Can LLMs Predict the Outcomes of Scientific Experiments in Natural Sciences?","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17843","citing_title":"Learning from AVA: Early Lessons from a Curated and Trustworthy Generative AI for Policy and Development Research","ref_index":120,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2KQVCP643X7UESPS4O7MNJDIRW","json":"https://pith.science/pith/2KQVCP643X7UESPS4O7MNJDIRW.json","graph_json":"https://pith.science/api/pith-number/2KQVCP643X7UESPS4O7MNJDIRW/graph.json","events_json":"https://pith.science/api/pith-number/2KQVCP643X7UESPS4O7MNJDIRW/events.json","paper":"https://pith.science/paper/2KQVCP64"},"agent_actions":{"view_html":"https://pith.science/pith/2KQVCP643X7UESPS4O7MNJDIRW","download_json":"https://pith.science/pith/2KQVCP643X7UESPS4O7MNJDIRW.json","view_paper":"https://pith.science/paper/2KQVCP64","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18153&json=true","fetch_graph":"https://pith.science/api/pith-number/2KQVCP643X7UESPS4O7MNJDIRW/graph.json","fetch_events":"https://pith.science/api/pith-number/2KQVCP643X7UESPS4O7MNJDIRW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2KQVCP643X7UESPS4O7MNJDIRW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2KQVCP643X7UESPS4O7MNJDIRW/action/storage_attestation","attest_author":"https://pith.science/pith/2KQVCP643X7UESPS4O7MNJDIRW/action/author_attestation","sign_citation":"https://pith.science/pith/2KQVCP643X7UESPS4O7MNJDIRW/action/citation_signature","submit_replication":"https://pith.science/pith/2KQVCP643X7UESPS4O7MNJDIRW/action/replication_record"}},"created_at":"2026-07-05T06:15:33.265219+00:00","updated_at":"2026-07-05T06:15:33.265219+00:00"}