{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WE7OSIKB2GDF47CR6O6A5LMCSV","short_pith_number":"pith:WE7OSIKB","schema_version":"1.0","canonical_sha256":"b13ee92141d1865e7c51f3bc0ead8295744622ae50eccf770003798f84867ec7","source":{"kind":"arxiv","id":"2410.14309","version":4},"attestation_state":"computed","paper":{"title":"LoGU: Long-form Generation with Uncertainty Expressions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Caiqi Zhang, Deqing Yang, Dong Yu, Nigel Collier, Ruihan Yang, Sen Yang, Xinting Huang, Zhisong Zhang","submitted_at":"2024-10-18T09:15:35Z","abstract_excerpt":"While Large Language Models (LLMs) demonstrate impressive capabilities, they still struggle with generating factually incorrect content (i.e., hallucinations). A promising approach to mitigate this issue is enabling models to express uncertainty when unsure. Previous research on uncertainty modeling has primarily focused on short-form QA, but realworld applications often require much longer responses. In this work, we introduce the task of Long-form Generation with Uncertainty(LoGU). We identify two key challenges: Uncertainty Suppression, where models hesitate to express uncertainty, and Unce"},"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":"2410.14309","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-18T09:15:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d90408cf036970be2152a88af77f4004a9efa84e1018b29240c1830cb269a6cb","abstract_canon_sha256":"53a99770e483305a059e55bee843496832145f50db1c4a99854430efb87d9611"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:39.961868Z","signature_b64":"D8yTseA1UXJdTBH+6529ZVgwzN4FZmGFAg3XzE1tvduQYfJnt3TpglHXKxjOjvTXcRIjYWqqlevvlgAYIg5nDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b13ee92141d1865e7c51f3bc0ead8295744622ae50eccf770003798f84867ec7","last_reissued_at":"2026-07-05T11:15:39.961372Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:39.961372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LoGU: Long-form Generation with Uncertainty Expressions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Caiqi Zhang, Deqing Yang, Dong Yu, Nigel Collier, Ruihan Yang, Sen Yang, Xinting Huang, Zhisong Zhang","submitted_at":"2024-10-18T09:15:35Z","abstract_excerpt":"While Large Language Models (LLMs) demonstrate impressive capabilities, they still struggle with generating factually incorrect content (i.e., hallucinations). A promising approach to mitigate this issue is enabling models to express uncertainty when unsure. Previous research on uncertainty modeling has primarily focused on short-form QA, but realworld applications often require much longer responses. In this work, we introduce the task of Long-form Generation with Uncertainty(LoGU). We identify two key challenges: Uncertainty Suppression, where models hesitate to express uncertainty, and Unce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14309","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/2410.14309/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":"2410.14309","created_at":"2026-07-05T11:15:39.961436+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.14309v4","created_at":"2026-07-05T11:15:39.961436+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14309","created_at":"2026-07-05T11:15:39.961436+00:00"},{"alias_kind":"pith_short_12","alias_value":"WE7OSIKB2GDF","created_at":"2026-07-05T11:15:39.961436+00:00"},{"alias_kind":"pith_short_16","alias_value":"WE7OSIKB2GDF47CR","created_at":"2026-07-05T11:15:39.961436+00:00"},{"alias_kind":"pith_short_8","alias_value":"WE7OSIKB","created_at":"2026-07-05T11:15:39.961436+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.23912","citing_title":"LoVeC: Reinforcement Learning for Better Verbalized Confidence in Long-Form Generations","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2509.09438","citing_title":"GrACE: A Generative Approach to Better Confidence Elicitation and Efficient Test-Time Scaling in Large Language Models","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WE7OSIKB2GDF47CR6O6A5LMCSV","json":"https://pith.science/pith/WE7OSIKB2GDF47CR6O6A5LMCSV.json","graph_json":"https://pith.science/api/pith-number/WE7OSIKB2GDF47CR6O6A5LMCSV/graph.json","events_json":"https://pith.science/api/pith-number/WE7OSIKB2GDF47CR6O6A5LMCSV/events.json","paper":"https://pith.science/paper/WE7OSIKB"},"agent_actions":{"view_html":"https://pith.science/pith/WE7OSIKB2GDF47CR6O6A5LMCSV","download_json":"https://pith.science/pith/WE7OSIKB2GDF47CR6O6A5LMCSV.json","view_paper":"https://pith.science/paper/WE7OSIKB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.14309&json=true","fetch_graph":"https://pith.science/api/pith-number/WE7OSIKB2GDF47CR6O6A5LMCSV/graph.json","fetch_events":"https://pith.science/api/pith-number/WE7OSIKB2GDF47CR6O6A5LMCSV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WE7OSIKB2GDF47CR6O6A5LMCSV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WE7OSIKB2GDF47CR6O6A5LMCSV/action/storage_attestation","attest_author":"https://pith.science/pith/WE7OSIKB2GDF47CR6O6A5LMCSV/action/author_attestation","sign_citation":"https://pith.science/pith/WE7OSIKB2GDF47CR6O6A5LMCSV/action/citation_signature","submit_replication":"https://pith.science/pith/WE7OSIKB2GDF47CR6O6A5LMCSV/action/replication_record"}},"created_at":"2026-07-05T11:15:39.961436+00:00","updated_at":"2026-07-05T11:15:39.961436+00:00"}