{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XF2LF7Q64AMRCWS25CJ2EMAAMN","short_pith_number":"pith:XF2LF7Q6","schema_version":"1.0","canonical_sha256":"b974b2fe1ee019115a5ae893a230006352813d20ac100cd0b34fecb8ed668a0d","source":{"kind":"arxiv","id":"2409.12180","version":1},"attestation_state":"computed","paper":{"title":"Finetuning Language Models to Emit Linguistic Expressions of Uncertainty","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Arslan Chaudhry, Dilan Gorur, Sridhar Thiagarajan","submitted_at":"2024-09-18T17:52:53Z","abstract_excerpt":"Large language models (LLMs) are increasingly employed in information-seeking and decision-making tasks. Despite their broad utility, LLMs tend to generate information that conflicts with real-world facts, and their persuasive style can make these inaccuracies appear confident and convincing. As a result, end-users struggle to consistently align the confidence expressed by LLMs with the accuracy of their predictions, often leading to either blind trust in all outputs or a complete disregard for their reliability. In this work, we explore supervised finetuning on uncertainty-augmented 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":"2409.12180","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-18T17:52:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c9d4ca19da7cb7fb475c0081b97686c3798b7529ed43dc016f00b855c09e6d9b","abstract_canon_sha256":"487d65e039accb6346c5e63d84d3c2eb136ba057b1403451330c4fd99d567e76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:44.001131Z","signature_b64":"CNJvVmf3LA2hjT7CLpnl1hn7Bv2/tSn48Wd+6SmAiUvdEHmrfrpPRM0fAJnkqh9BtLoNbglfbRPwJIPyfFsyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b974b2fe1ee019115a5ae893a230006352813d20ac100cd0b34fecb8ed668a0d","last_reissued_at":"2026-07-05T09:08:44.000579Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:44.000579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finetuning Language Models to Emit Linguistic Expressions of Uncertainty","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Arslan Chaudhry, Dilan Gorur, Sridhar Thiagarajan","submitted_at":"2024-09-18T17:52:53Z","abstract_excerpt":"Large language models (LLMs) are increasingly employed in information-seeking and decision-making tasks. Despite their broad utility, LLMs tend to generate information that conflicts with real-world facts, and their persuasive style can make these inaccuracies appear confident and convincing. As a result, end-users struggle to consistently align the confidence expressed by LLMs with the accuracy of their predictions, often leading to either blind trust in all outputs or a complete disregard for their reliability. In this work, we explore supervised finetuning on uncertainty-augmented predictio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12180","kind":"arxiv","version":1},"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/2409.12180/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":"2409.12180","created_at":"2026-07-05T09:08:44.000641+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.12180v1","created_at":"2026-07-05T09:08:44.000641+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12180","created_at":"2026-07-05T09:08:44.000641+00:00"},{"alias_kind":"pith_short_12","alias_value":"XF2LF7Q64AMR","created_at":"2026-07-05T09:08:44.000641+00:00"},{"alias_kind":"pith_short_16","alias_value":"XF2LF7Q64AMRCWS2","created_at":"2026-07-05T09:08:44.000641+00:00"},{"alias_kind":"pith_short_8","alias_value":"XF2LF7Q6","created_at":"2026-07-05T09:08:44.000641+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27023","citing_title":"Just how sure are you? Improving Verbalized Uncertainty Calibration in Medical VQA","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.32032","citing_title":"Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28778","citing_title":"Can LLMs Use Linguistic Uncertainty Markers to Reliably Reflect Intrinsic Confidence?","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10893","citing_title":"Grounded or Guessing? LVLM Confidence Estimation via Blind-Image Contrastive Ranking","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13595","citing_title":"Inducing Artificial Uncertainty in Language Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10893","citing_title":"Grounded or Guessing? LVLM Confidence Estimation via Blind-Image Contrastive Ranking","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XF2LF7Q64AMRCWS25CJ2EMAAMN","json":"https://pith.science/pith/XF2LF7Q64AMRCWS25CJ2EMAAMN.json","graph_json":"https://pith.science/api/pith-number/XF2LF7Q64AMRCWS25CJ2EMAAMN/graph.json","events_json":"https://pith.science/api/pith-number/XF2LF7Q64AMRCWS25CJ2EMAAMN/events.json","paper":"https://pith.science/paper/XF2LF7Q6"},"agent_actions":{"view_html":"https://pith.science/pith/XF2LF7Q64AMRCWS25CJ2EMAAMN","download_json":"https://pith.science/pith/XF2LF7Q64AMRCWS25CJ2EMAAMN.json","view_paper":"https://pith.science/paper/XF2LF7Q6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.12180&json=true","fetch_graph":"https://pith.science/api/pith-number/XF2LF7Q64AMRCWS25CJ2EMAAMN/graph.json","fetch_events":"https://pith.science/api/pith-number/XF2LF7Q64AMRCWS25CJ2EMAAMN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XF2LF7Q64AMRCWS25CJ2EMAAMN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XF2LF7Q64AMRCWS25CJ2EMAAMN/action/storage_attestation","attest_author":"https://pith.science/pith/XF2LF7Q64AMRCWS25CJ2EMAAMN/action/author_attestation","sign_citation":"https://pith.science/pith/XF2LF7Q64AMRCWS25CJ2EMAAMN/action/citation_signature","submit_replication":"https://pith.science/pith/XF2LF7Q64AMRCWS25CJ2EMAAMN/action/replication_record"}},"created_at":"2026-07-05T09:08:44.000641+00:00","updated_at":"2026-07-05T09:08:44.000641+00:00"}