{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AN4QUOOUPWPFBCDS4D3KDMZ7O2","short_pith_number":"pith:AN4QUOOU","schema_version":"1.0","canonical_sha256":"03790a39d47d9e508872e0f6a1b33f76ae5dc2fb1c425ce258968b420002d729","source":{"kind":"arxiv","id":"2506.16064","version":1},"attestation_state":"computed","paper":{"title":"Self-Critique-Guided Curiosity Refinement: Enhancing Honesty and Helpfulness in Large Language Models via In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenglin Fan, Duc Hieu Ho","submitted_at":"2025-06-19T06:42:35Z","abstract_excerpt":"Large language models (LLMs) have demonstrated robust capabilities across various natural language tasks. However, producing outputs that are consistently honest and helpful remains an open challenge. To overcome this challenge, this paper tackles the problem through two complementary directions. It conducts a comprehensive benchmark evaluation of ten widely used large language models, including both proprietary and open-weight models from OpenAI, Meta, and Google. In parallel, it proposes a novel prompting strategy, self-critique-guided curiosity refinement prompting. The key idea behind this"},"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":"2506.16064","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-19T06:42:35Z","cross_cats_sorted":[],"title_canon_sha256":"a3e73cc54039697b2558d9d4c2611c5f62325d3eb9ab54ea9f5577fdc9894818","abstract_canon_sha256":"b0f983068e28ac7acfc244953dbaac99109a7f7cad87d84049de347642d1e936"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:29.644682Z","signature_b64":"d1hToNNfUvG5DBdpM8TO/xYvtRYeGlgUP8aaKKhAu8QcBnIQgBW+ug8Yi30TXnfj5L8tLvrDfVRcvPZUQs0SDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03790a39d47d9e508872e0f6a1b33f76ae5dc2fb1c425ce258968b420002d729","last_reissued_at":"2026-07-05T11:24:29.644198Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:29.644198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Critique-Guided Curiosity Refinement: Enhancing Honesty and Helpfulness in Large Language Models via In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenglin Fan, Duc Hieu Ho","submitted_at":"2025-06-19T06:42:35Z","abstract_excerpt":"Large language models (LLMs) have demonstrated robust capabilities across various natural language tasks. However, producing outputs that are consistently honest and helpful remains an open challenge. To overcome this challenge, this paper tackles the problem through two complementary directions. It conducts a comprehensive benchmark evaluation of ten widely used large language models, including both proprietary and open-weight models from OpenAI, Meta, and Google. In parallel, it proposes a novel prompting strategy, self-critique-guided curiosity refinement prompting. The key idea behind this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16064","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/2506.16064/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":"2506.16064","created_at":"2026-07-05T11:24:29.644258+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.16064v1","created_at":"2026-07-05T11:24:29.644258+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16064","created_at":"2026-07-05T11:24:29.644258+00:00"},{"alias_kind":"pith_short_12","alias_value":"AN4QUOOUPWPF","created_at":"2026-07-05T11:24:29.644258+00:00"},{"alias_kind":"pith_short_16","alias_value":"AN4QUOOUPWPFBCDS","created_at":"2026-07-05T11:24:29.644258+00:00"},{"alias_kind":"pith_short_8","alias_value":"AN4QUOOU","created_at":"2026-07-05T11:24:29.644258+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AN4QUOOUPWPFBCDS4D3KDMZ7O2","json":"https://pith.science/pith/AN4QUOOUPWPFBCDS4D3KDMZ7O2.json","graph_json":"https://pith.science/api/pith-number/AN4QUOOUPWPFBCDS4D3KDMZ7O2/graph.json","events_json":"https://pith.science/api/pith-number/AN4QUOOUPWPFBCDS4D3KDMZ7O2/events.json","paper":"https://pith.science/paper/AN4QUOOU"},"agent_actions":{"view_html":"https://pith.science/pith/AN4QUOOUPWPFBCDS4D3KDMZ7O2","download_json":"https://pith.science/pith/AN4QUOOUPWPFBCDS4D3KDMZ7O2.json","view_paper":"https://pith.science/paper/AN4QUOOU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.16064&json=true","fetch_graph":"https://pith.science/api/pith-number/AN4QUOOUPWPFBCDS4D3KDMZ7O2/graph.json","fetch_events":"https://pith.science/api/pith-number/AN4QUOOUPWPFBCDS4D3KDMZ7O2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AN4QUOOUPWPFBCDS4D3KDMZ7O2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AN4QUOOUPWPFBCDS4D3KDMZ7O2/action/storage_attestation","attest_author":"https://pith.science/pith/AN4QUOOUPWPFBCDS4D3KDMZ7O2/action/author_attestation","sign_citation":"https://pith.science/pith/AN4QUOOUPWPFBCDS4D3KDMZ7O2/action/citation_signature","submit_replication":"https://pith.science/pith/AN4QUOOUPWPFBCDS4D3KDMZ7O2/action/replication_record"}},"created_at":"2026-07-05T11:24:29.644258+00:00","updated_at":"2026-07-05T11:24:29.644258+00:00"}