{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5Q3AWTYBMMWH57MHJHWFGJZIY7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5e8ece653820736dc8f495ead849add660353adc0eec363e4ed153d05b853e15","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T01:37:23Z","title_canon_sha256":"d9d09b6cc2160b5e299d612fab071e5e3e17a66db1ad95ffd6f6df4875007387"},"schema_version":"1.0","source":{"id":"2402.17124","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17124","created_at":"2026-07-05T09:04:33Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17124v2","created_at":"2026-07-05T09:04:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17124","created_at":"2026-07-05T09:04:33Z"},{"alias_kind":"pith_short_12","alias_value":"5Q3AWTYBMMWH","created_at":"2026-07-05T09:04:33Z"},{"alias_kind":"pith_short_16","alias_value":"5Q3AWTYBMMWH57MH","created_at":"2026-07-05T09:04:33Z"},{"alias_kind":"pith_short_8","alias_value":"5Q3AWTYB","created_at":"2026-07-05T09:04:33Z"}],"graph_snapshots":[{"event_id":"sha256:1530134fbc0b3ae5135eb7400e637d4c75d2d426814243d157a75e6488a01f93","target":"graph","created_at":"2026-07-05T09:04:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.17124/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For a LLM to be trustworthy, its confidence level should be well-calibrated with its actual performance. While it is now common sense that LLM performances are greatly impacted by prompts, the confidence calibration in prompting LLMs has yet to be thoroughly explored. In this paper, we explore how different prompting strategies influence LLM confidence calibration and how it could be improved. We conduct extensive experiments on six prompting methods in the question-answering context and we observe that, while these methods help improve the expected LLM calibration, they also trigger LLMs to b","authors_text":"Dong Yu, Hongming Zhang, Jianshu Chen, Tongshuang Wu, Wenlin Yao, Xiaoman Pan, Xinran Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T01:37:23Z","title":"Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17124","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6a4f993288ff180072d0485f343109e60a9ae3365193004b947c47a8701b1e92","target":"record","created_at":"2026-07-05T09:04:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5e8ece653820736dc8f495ead849add660353adc0eec363e4ed153d05b853e15","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T01:37:23Z","title_canon_sha256":"d9d09b6cc2160b5e299d612fab071e5e3e17a66db1ad95ffd6f6df4875007387"},"schema_version":"1.0","source":{"id":"2402.17124","kind":"arxiv","version":2}},"canonical_sha256":"ec360b4f01632c7efd8749ec532728c7d0f3fb47ef5c67f0d6aa5f786b997407","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec360b4f01632c7efd8749ec532728c7d0f3fb47ef5c67f0d6aa5f786b997407","first_computed_at":"2026-07-05T09:04:33.028008Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:04:33.028008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AaDW2ZwmTQwV8zPuf5/EiAdspUTCxaYx/M9Grzo+iy2OXULY/hjejDHL69RMQXqPxzPNZckxbCqxWvHMRd/wDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:04:33.028433Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.17124","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a4f993288ff180072d0485f343109e60a9ae3365193004b947c47a8701b1e92","sha256:1530134fbc0b3ae5135eb7400e637d4c75d2d426814243d157a75e6488a01f93"],"state_sha256":"83c499d3317344a992bee1020399b31c911802b25473b7e7bb0a0c4467d6c213"}