{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6R5FUZARBCYDPHKC64H74C46EV","short_pith_number":"pith:6R5FUZAR","schema_version":"1.0","canonical_sha256":"f47a5a641108b0379d42f70ffe0b9e2546cd0e084fdb8830c0a5660327f69d83","source":{"kind":"arxiv","id":"2311.08298","version":2},"attestation_state":"computed","paper":{"title":"A Survey of Confidence Estimation and Calibration in Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fengyu Cai, Heinz Koeppl, Iryna Gurevych, Jiahui Geng, Preslav Nakov, Yuxia Wang","submitted_at":"2023-11-14T16:43:29Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks in various domains. Despite their impressive performance, they can be unreliable due to factual errors in their generations. Assessing their confidence and calibrating them across different tasks can help mitigate risks and enable LLMs to produce better generations. There has been a lot of recent research aiming to address this, but there has been no comprehensive overview to organize it and outline the main lessons learned. The present survey aims to bridge this gap. In particular, we outline t"},"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":"2311.08298","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-14T16:43:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f5ab0cee5b32242b6b9416b7ec1795eec1caa6962a50fadd0a19cdafc775fb4d","abstract_canon_sha256":"7512bbb60b5805da73932d64262c9f147c57f4af0a12af4fccc226be68906008"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:57.086863Z","signature_b64":"I6sAf5mphxIdOpulWRSjCh2c9/RaFVDNUdGcrthCHGrtrM7WpJk77q8rWjiLFZ9Sqe+JRLXV0vkoAWSqd3U1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f47a5a641108b0379d42f70ffe0b9e2546cd0e084fdb8830c0a5660327f69d83","last_reissued_at":"2026-07-05T07:59:57.086441Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:57.086441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Confidence Estimation and Calibration in Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fengyu Cai, Heinz Koeppl, Iryna Gurevych, Jiahui Geng, Preslav Nakov, Yuxia Wang","submitted_at":"2023-11-14T16:43:29Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks in various domains. Despite their impressive performance, they can be unreliable due to factual errors in their generations. Assessing their confidence and calibrating them across different tasks can help mitigate risks and enable LLMs to produce better generations. There has been a lot of recent research aiming to address this, but there has been no comprehensive overview to organize it and outline the main lessons learned. The present survey aims to bridge this gap. In particular, we outline t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08298","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/2311.08298/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":"2311.08298","created_at":"2026-07-05T07:59:57.086504+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.08298v2","created_at":"2026-07-05T07:59:57.086504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08298","created_at":"2026-07-05T07:59:57.086504+00:00"},{"alias_kind":"pith_short_12","alias_value":"6R5FUZARBCYD","created_at":"2026-07-05T07:59:57.086504+00:00"},{"alias_kind":"pith_short_16","alias_value":"6R5FUZARBCYDPHKC","created_at":"2026-07-05T07:59:57.086504+00:00"},{"alias_kind":"pith_short_8","alias_value":"6R5FUZAR","created_at":"2026-07-05T07:59:57.086504+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.08065","citing_title":"When LLMs Agree, Are They Right? Auditing Self-Consistency and Cross-Model Agreement as Confidence Signals","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2607.06327","citing_title":"Estimating Uncertainty from Reasoning: A Large-Scale Study of Multi- and Crosslingual MCQA Performance in LLMs","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21937","citing_title":"Latent Confidence Alignment for LLM Self-Assessment","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19950","citing_title":"Confidence Calibration for Multimodal LLMs: An Empirical Study through Medical VQA","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29654","citing_title":"Budgeted Act-or-Defer Multi-Agent LLM Deliberation with Local Reliability Bounds","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2408.10692","citing_title":"Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2603.17839","citing_title":"How do LLMs Compute Verbal Confidence","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19220","citing_title":"Position: Uncertainty Quantification in LLMs is Just Unsupervised Clustering","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2509.05489","citing_title":"Self-Aligned Reward: Towards Effective and Efficient Reasoners","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2511.09803","citing_title":"Retrieval as a Decision: Training-Free Adaptive Gating for Efficient RAG","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08221","citing_title":"NoisyCoconut: Counterfactual Consensus via Latent Space Reasoning","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22215","citing_title":"Verbal Confidence Saturation in 3-9B Open-Weight Instruction-Tuned LLMs: A Pre-Registered Psychometric Validity Screen","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22271","citing_title":"How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12491","citing_title":"Calibrated Confidence Estimation for Tabular Question Answering","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06812","citing_title":"AGSC: Adaptive Granularity and Semantic Clustering for Uncertainty Quantification in Long-text Generation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17200","citing_title":"Calibrating Model-Based Evaluation Metrics for Summarization","ref_index":74,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6R5FUZARBCYDPHKC64H74C46EV","json":"https://pith.science/pith/6R5FUZARBCYDPHKC64H74C46EV.json","graph_json":"https://pith.science/api/pith-number/6R5FUZARBCYDPHKC64H74C46EV/graph.json","events_json":"https://pith.science/api/pith-number/6R5FUZARBCYDPHKC64H74C46EV/events.json","paper":"https://pith.science/paper/6R5FUZAR"},"agent_actions":{"view_html":"https://pith.science/pith/6R5FUZARBCYDPHKC64H74C46EV","download_json":"https://pith.science/pith/6R5FUZARBCYDPHKC64H74C46EV.json","view_paper":"https://pith.science/paper/6R5FUZAR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.08298&json=true","fetch_graph":"https://pith.science/api/pith-number/6R5FUZARBCYDPHKC64H74C46EV/graph.json","fetch_events":"https://pith.science/api/pith-number/6R5FUZARBCYDPHKC64H74C46EV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6R5FUZARBCYDPHKC64H74C46EV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6R5FUZARBCYDPHKC64H74C46EV/action/storage_attestation","attest_author":"https://pith.science/pith/6R5FUZARBCYDPHKC64H74C46EV/action/author_attestation","sign_citation":"https://pith.science/pith/6R5FUZARBCYDPHKC64H74C46EV/action/citation_signature","submit_replication":"https://pith.science/pith/6R5FUZARBCYDPHKC64H74C46EV/action/replication_record"}},"created_at":"2026-07-05T07:59:57.086504+00:00","updated_at":"2026-07-05T07:59:57.086504+00:00"}