{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VSR3DGPKPPQOB7I64TBSN3AXJG","short_pith_number":"pith:VSR3DGPK","schema_version":"1.0","canonical_sha256":"aca3b199ea7be0e0fd1ee4c326ec1749ab82af505a9f327f6744f868bcff2a4d","source":{"kind":"arxiv","id":"2305.18404","version":3},"attestation_state":"computed","paper":{"title":"Conformal Prediction with Large Language Models for Multi-Choice Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Andrew Beam, Anil Palepu, Bhawesh Kumar, Charlie Lu, David Bellamy, Gauri Gupta, Ramesh Raskar","submitted_at":"2023-05-28T15:26:10Z","abstract_excerpt":"As large language models continue to be widely developed, robust uncertainty quantification techniques will become crucial for their safe deployment in high-stakes scenarios. In this work, we explore how conformal prediction can be used to provide uncertainty quantification in language models for the specific task of multiple-choice question-answering. We find that the uncertainty estimates from conformal prediction are tightly correlated with prediction accuracy. This observation can be useful for downstream applications such as selective classification and filtering out low-quality predictio"},"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":"2305.18404","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-28T15:26:10Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"876a9a85ade0b532274a3d7208ce76dd34780b30f42723410ae2e394c9f28c3f","abstract_canon_sha256":"b4ab67460624b21c03cd2337072b1590ad2404ed82cfec16675ddce2eb6453cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:29:02.121536Z","signature_b64":"3u/f5kK7eM4yjR3XJeaAyg2/uFR9Rl6w/CN6xICESClnNqWzvj6YDWHUvf3gNRjJVJs7S1BFEJeDSo//IBR9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aca3b199ea7be0e0fd1ee4c326ec1749ab82af505a9f327f6744f868bcff2a4d","last_reissued_at":"2026-07-05T06:29:02.121000Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:29:02.121000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conformal Prediction with Large Language Models for Multi-Choice Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Andrew Beam, Anil Palepu, Bhawesh Kumar, Charlie Lu, David Bellamy, Gauri Gupta, Ramesh Raskar","submitted_at":"2023-05-28T15:26:10Z","abstract_excerpt":"As large language models continue to be widely developed, robust uncertainty quantification techniques will become crucial for their safe deployment in high-stakes scenarios. In this work, we explore how conformal prediction can be used to provide uncertainty quantification in language models for the specific task of multiple-choice question-answering. We find that the uncertainty estimates from conformal prediction are tightly correlated with prediction accuracy. This observation can be useful for downstream applications such as selective classification and filtering out low-quality predictio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18404","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/2305.18404/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":"2305.18404","created_at":"2026-07-05T06:29:02.121064+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18404v3","created_at":"2026-07-05T06:29:02.121064+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18404","created_at":"2026-07-05T06:29:02.121064+00:00"},{"alias_kind":"pith_short_12","alias_value":"VSR3DGPKPPQO","created_at":"2026-07-05T06:29:02.121064+00:00"},{"alias_kind":"pith_short_16","alias_value":"VSR3DGPKPPQOB7I6","created_at":"2026-07-05T06:29:02.121064+00:00"},{"alias_kind":"pith_short_8","alias_value":"VSR3DGPK","created_at":"2026-07-05T06:29:02.121064+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22792","citing_title":"The Origins of Stochasticity: Comprehensive Investigations on Uncertainty Quantification for Large Language Models","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12587","citing_title":"Strategic Decision Support for AI Agents","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01850","citing_title":"Does Compression Preserve Uncertainty? A Unified Benchmark for Quantized and Sparse LLMs via Conformal Prediction","ref_index":50,"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":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27091","citing_title":"MiRD: Reliable Set-Valued Prediction for Open-Ended Question Answering via Miscoverage Risk Decomposition","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28264","citing_title":"Entropy Distribution as a Fingerprint for Hallucinations in Generative Models","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30085","citing_title":"Conformal Certification of Reasoning Trace Prefixes","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00251","citing_title":"Capability Self-Assessment: Teaching LLMs to Know Their Limits","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22864","citing_title":"Reading Calibrated Uncertainty from Language Model Trajectories","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2412.02904","citing_title":"Enhancing Trust in Large Language Models via Uncertainty-Calibrated Fine-Tuning","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2602.01733","citing_title":"Improving Backward Conformal Prediction via Non-Conformity Score Transformation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":215,"is_internal_anchor":false},{"citing_arxiv_id":"2308.05374","citing_title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","ref_index":116,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01413","citing_title":"Adaptive Stopping for Multi-Turn LLM Reasoning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12195","citing_title":"Fair Conformal Classification via Learning Representation-Based Groups","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12201","citing_title":"Uncertainty Quantification for LLM-based Code Generation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27914","citing_title":"Geometry-Calibrated Conformal Abstention for Language Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25235","citing_title":"VLM Judges Can Rank but Cannot Score: Task-Dependent Uncertainty in Multimodal Evaluation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23987","citing_title":"Continual Calibration: Coverage Can Collapse Before Accuracy in Lifelong LLM Fine-Tuning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12491","citing_title":"Calibrated Confidence Estimation for Tabular Question Answering","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15302","citing_title":"Diagnosing LLM Judge Reliability: Conformal Prediction Sets and Transitivity Violations","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VSR3DGPKPPQOB7I64TBSN3AXJG","json":"https://pith.science/pith/VSR3DGPKPPQOB7I64TBSN3AXJG.json","graph_json":"https://pith.science/api/pith-number/VSR3DGPKPPQOB7I64TBSN3AXJG/graph.json","events_json":"https://pith.science/api/pith-number/VSR3DGPKPPQOB7I64TBSN3AXJG/events.json","paper":"https://pith.science/paper/VSR3DGPK"},"agent_actions":{"view_html":"https://pith.science/pith/VSR3DGPKPPQOB7I64TBSN3AXJG","download_json":"https://pith.science/pith/VSR3DGPKPPQOB7I64TBSN3AXJG.json","view_paper":"https://pith.science/paper/VSR3DGPK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18404&json=true","fetch_graph":"https://pith.science/api/pith-number/VSR3DGPKPPQOB7I64TBSN3AXJG/graph.json","fetch_events":"https://pith.science/api/pith-number/VSR3DGPKPPQOB7I64TBSN3AXJG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VSR3DGPKPPQOB7I64TBSN3AXJG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VSR3DGPKPPQOB7I64TBSN3AXJG/action/storage_attestation","attest_author":"https://pith.science/pith/VSR3DGPKPPQOB7I64TBSN3AXJG/action/author_attestation","sign_citation":"https://pith.science/pith/VSR3DGPKPPQOB7I64TBSN3AXJG/action/citation_signature","submit_replication":"https://pith.science/pith/VSR3DGPKPPQOB7I64TBSN3AXJG/action/replication_record"}},"created_at":"2026-07-05T06:29:02.121064+00:00","updated_at":"2026-07-05T06:29:02.121064+00:00"}