{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QSASV377CZOQP2BTPBIQ2GGDIQ","short_pith_number":"pith:QSASV377","schema_version":"1.0","canonical_sha256":"84812aefff165d07e83378510d18c34424c979822a525d40a2f9f24cbae17a8c","source":{"kind":"arxiv","id":"2409.09629","version":2},"attestation_state":"computed","paper":{"title":"Confidence Estimation for LLM-Based Dialogue State Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dilek Hakkani-Tur, Gokhan Tur, Suvodip Dey, Yi-Jyun Sun","submitted_at":"2024-09-15T06:44:26Z","abstract_excerpt":"Estimation of a model's confidence on its outputs is critical for Conversational AI systems based on large language models (LLMs), especially for reducing hallucination and preventing over-reliance. In this work, we provide an exhaustive exploration of methods, including approaches proposed for open- and closed-weight LLMs, aimed at quantifying and leveraging model uncertainty to improve the reliability of LLM-generated responses, specifically focusing on dialogue state tracking (DST) in task-oriented dialogue systems (TODS). Regardless of the model type, well-calibrated confidence scores are "},"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":"2409.09629","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-15T06:44:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d9a4e89f6a9f5797b254f9ef0e2f6d97e617f9511fa5aeb6ec217b508aee496a","abstract_canon_sha256":"91add80548b3bd6c30b1a7d33afb24def7bcabbef1338a6c443d7c2f96adc0b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:04.298980Z","signature_b64":"8gqIJcQYbjTtcFvU0UmewGiT1DCX7rc0VkBDg+mE8lc6wWMdKHQ4T/qe9QSVwKYghFl2RZWVC1ZnF7n9sr15Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84812aefff165d07e83378510d18c34424c979822a525d40a2f9f24cbae17a8c","last_reissued_at":"2026-07-05T09:10:04.298493Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:04.298493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Confidence Estimation for LLM-Based Dialogue State Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dilek Hakkani-Tur, Gokhan Tur, Suvodip Dey, Yi-Jyun Sun","submitted_at":"2024-09-15T06:44:26Z","abstract_excerpt":"Estimation of a model's confidence on its outputs is critical for Conversational AI systems based on large language models (LLMs), especially for reducing hallucination and preventing over-reliance. In this work, we provide an exhaustive exploration of methods, including approaches proposed for open- and closed-weight LLMs, aimed at quantifying and leveraging model uncertainty to improve the reliability of LLM-generated responses, specifically focusing on dialogue state tracking (DST) in task-oriented dialogue systems (TODS). Regardless of the model type, well-calibrated confidence scores are "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09629","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/2409.09629/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":"2409.09629","created_at":"2026-07-05T09:10:04.298547+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.09629v2","created_at":"2026-07-05T09:10:04.298547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09629","created_at":"2026-07-05T09:10:04.298547+00:00"},{"alias_kind":"pith_short_12","alias_value":"QSASV377CZOQ","created_at":"2026-07-05T09:10:04.298547+00:00"},{"alias_kind":"pith_short_16","alias_value":"QSASV377CZOQP2BT","created_at":"2026-07-05T09:10:04.298547+00:00"},{"alias_kind":"pith_short_8","alias_value":"QSASV377","created_at":"2026-07-05T09:10:04.298547+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00543","citing_title":"Reliable Annotations with Less Effort: Evaluating LLM-Human Collaboration in Search Clarifications","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QSASV377CZOQP2BTPBIQ2GGDIQ","json":"https://pith.science/pith/QSASV377CZOQP2BTPBIQ2GGDIQ.json","graph_json":"https://pith.science/api/pith-number/QSASV377CZOQP2BTPBIQ2GGDIQ/graph.json","events_json":"https://pith.science/api/pith-number/QSASV377CZOQP2BTPBIQ2GGDIQ/events.json","paper":"https://pith.science/paper/QSASV377"},"agent_actions":{"view_html":"https://pith.science/pith/QSASV377CZOQP2BTPBIQ2GGDIQ","download_json":"https://pith.science/pith/QSASV377CZOQP2BTPBIQ2GGDIQ.json","view_paper":"https://pith.science/paper/QSASV377","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.09629&json=true","fetch_graph":"https://pith.science/api/pith-number/QSASV377CZOQP2BTPBIQ2GGDIQ/graph.json","fetch_events":"https://pith.science/api/pith-number/QSASV377CZOQP2BTPBIQ2GGDIQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QSASV377CZOQP2BTPBIQ2GGDIQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QSASV377CZOQP2BTPBIQ2GGDIQ/action/storage_attestation","attest_author":"https://pith.science/pith/QSASV377CZOQP2BTPBIQ2GGDIQ/action/author_attestation","sign_citation":"https://pith.science/pith/QSASV377CZOQP2BTPBIQ2GGDIQ/action/citation_signature","submit_replication":"https://pith.science/pith/QSASV377CZOQP2BTPBIQ2GGDIQ/action/replication_record"}},"created_at":"2026-07-05T09:10:04.298547+00:00","updated_at":"2026-07-05T09:10:04.298547+00:00"}