{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TKM6AVGVWEAJ2VU2QWQ5YOHDID","short_pith_number":"pith:TKM6AVGV","schema_version":"1.0","canonical_sha256":"9a99e054d5b1009d569a85a1dc38e340da007e1aa6f1071e9643768ab25c4d33","source":{"kind":"arxiv","id":"2406.15627","version":4},"attestation_state":"computed","paper":{"title":"Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Abdelrahman Boda Sadallah, Akim Tsvigun, Alexander Panchenko, Artem Shelmanov, Artem Vazhentsev, Daniil Vasilev, Ekaterina Fadeeva, Kirill Grishchenkov, Lyudmila Rvanova, Maxim Panov, Preslav Nakov, Roman Vashurin, Rui Xing, Sergey Petrakov, Timothy Baldwin","submitted_at":"2024-06-21T20:06:31Z","abstract_excerpt":"The rapid proliferation of large language models (LLMs) has stimulated researchers to seek effective and efficient approaches to deal with LLM hallucinations and low-quality outputs. Uncertainty quantification (UQ) is a key element of machine learning applications in dealing with such challenges. However, research to date on UQ for LLMs has been fragmented in terms of techniques and evaluation methodologies. In this work, we address this issue by introducing a novel benchmark that implements a collection of state-of-the-art UQ baselines and offers an environment for controllable and consistent"},"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":"2406.15627","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T20:06:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"26653d7001acef91b8e181d98895d04cf5b540102eb5d0590e39930d8ed8bb29","abstract_canon_sha256":"d440b514fcf68b3aa0dea048554278585fa3a1ce8bca244f5ed5bc0e29067d35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:59.894812Z","signature_b64":"1HxfV250sYWO/UrzO6U0xwRnOcgTM6AthbEWEe2jWPYXkkABLKsw1Svg/QFjUTvU9yADgrjtRpZxuevq1J95BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a99e054d5b1009d569a85a1dc38e340da007e1aa6f1071e9643768ab25c4d33","last_reissued_at":"2026-07-05T11:28:59.894276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:59.894276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Abdelrahman Boda Sadallah, Akim Tsvigun, Alexander Panchenko, Artem Shelmanov, Artem Vazhentsev, Daniil Vasilev, Ekaterina Fadeeva, Kirill Grishchenkov, Lyudmila Rvanova, Maxim Panov, Preslav Nakov, Roman Vashurin, Rui Xing, Sergey Petrakov, Timothy Baldwin","submitted_at":"2024-06-21T20:06:31Z","abstract_excerpt":"The rapid proliferation of large language models (LLMs) has stimulated researchers to seek effective and efficient approaches to deal with LLM hallucinations and low-quality outputs. Uncertainty quantification (UQ) is a key element of machine learning applications in dealing with such challenges. However, research to date on UQ for LLMs has been fragmented in terms of techniques and evaluation methodologies. In this work, we address this issue by introducing a novel benchmark that implements a collection of state-of-the-art UQ baselines and offers an environment for controllable and consistent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15627","kind":"arxiv","version":4},"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/2406.15627/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":"2406.15627","created_at":"2026-07-05T11:28:59.894325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.15627v4","created_at":"2026-07-05T11:28:59.894325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15627","created_at":"2026-07-05T11:28:59.894325+00:00"},{"alias_kind":"pith_short_12","alias_value":"TKM6AVGVWEAJ","created_at":"2026-07-05T11:28:59.894325+00:00"},{"alias_kind":"pith_short_16","alias_value":"TKM6AVGVWEAJ2VU2","created_at":"2026-07-05T11:28:59.894325+00:00"},{"alias_kind":"pith_short_8","alias_value":"TKM6AVGV","created_at":"2026-07-05T11:28:59.894325+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.14427","citing_title":"Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Models","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2503.18562","citing_title":"Self-Reported Confidence of Large Language Models in Gastroenterology: Analysis of Commercial, Open-Source, and Quantized Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19365","citing_title":"On-the-Fly Input Adaptation for Reliable Code Intelligence","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19369","citing_title":"When to Answer and When to Defer: A Decision Framework for Reliable Code Predictions","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TKM6AVGVWEAJ2VU2QWQ5YOHDID","json":"https://pith.science/pith/TKM6AVGVWEAJ2VU2QWQ5YOHDID.json","graph_json":"https://pith.science/api/pith-number/TKM6AVGVWEAJ2VU2QWQ5YOHDID/graph.json","events_json":"https://pith.science/api/pith-number/TKM6AVGVWEAJ2VU2QWQ5YOHDID/events.json","paper":"https://pith.science/paper/TKM6AVGV"},"agent_actions":{"view_html":"https://pith.science/pith/TKM6AVGVWEAJ2VU2QWQ5YOHDID","download_json":"https://pith.science/pith/TKM6AVGVWEAJ2VU2QWQ5YOHDID.json","view_paper":"https://pith.science/paper/TKM6AVGV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.15627&json=true","fetch_graph":"https://pith.science/api/pith-number/TKM6AVGVWEAJ2VU2QWQ5YOHDID/graph.json","fetch_events":"https://pith.science/api/pith-number/TKM6AVGVWEAJ2VU2QWQ5YOHDID/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TKM6AVGVWEAJ2VU2QWQ5YOHDID/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TKM6AVGVWEAJ2VU2QWQ5YOHDID/action/storage_attestation","attest_author":"https://pith.science/pith/TKM6AVGVWEAJ2VU2QWQ5YOHDID/action/author_attestation","sign_citation":"https://pith.science/pith/TKM6AVGVWEAJ2VU2QWQ5YOHDID/action/citation_signature","submit_replication":"https://pith.science/pith/TKM6AVGVWEAJ2VU2QWQ5YOHDID/action/replication_record"}},"created_at":"2026-07-05T11:28:59.894325+00:00","updated_at":"2026-07-05T11:28:59.894325+00:00"}