{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FKVGHVNPHFFYG4EVAV4LW7UOQV","short_pith_number":"pith:FKVGHVNP","schema_version":"1.0","canonical_sha256":"2aaa63d5af394b8370950578bb7e8e8543e5ca91f2a4fcc63adf0cd02ee9c1a6","source":{"kind":"arxiv","id":"2402.12563","version":3},"attestation_state":"computed","paper":{"title":"Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Eric Xing, Guangyi Chen, Kun Zhang, Loka Li, Yixuan Zhang, Yusheng Su, Zhenhao Chen","submitted_at":"2024-02-19T21:38:02Z","abstract_excerpt":"The recent success of Large Language Models (LLMs) has catalyzed an increasing interest in their self-correction capabilities. This paper presents a comprehensive investigation into the intrinsic self-correction of LLMs, attempting to address the ongoing debate about its feasibility. Our research has identified an important latent factor - the \"confidence\" of LLMs - during the self-correction process. Overlooking this factor may cause the models to over-criticize themselves, resulting in unreliable conclusions regarding the efficacy of self-correction. We have experimentally observed that LLMs"},"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":"2402.12563","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T21:38:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f69fba9dced1c47948d61ad4ac00693c95ed112065cdc66762ead7a08904e02c","abstract_canon_sha256":"f296fada3e3a6d665216768ee1a3b04c3855ed99dd6687b2d850d97785b27f45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:18:05.507529Z","signature_b64":"2KjmxdB2bhtIy4t6CSwWa1symTvGVK74040IA5bRl8dm06Z7yr5DQAqcecS5408eBXyD75qkoZFEgXz6ZoAZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2aaa63d5af394b8370950578bb7e8e8543e5ca91f2a4fcc63adf0cd02ee9c1a6","last_reissued_at":"2026-07-05T08:18:05.506941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:18:05.506941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Eric Xing, Guangyi Chen, Kun Zhang, Loka Li, Yixuan Zhang, Yusheng Su, Zhenhao Chen","submitted_at":"2024-02-19T21:38:02Z","abstract_excerpt":"The recent success of Large Language Models (LLMs) has catalyzed an increasing interest in their self-correction capabilities. This paper presents a comprehensive investigation into the intrinsic self-correction of LLMs, attempting to address the ongoing debate about its feasibility. Our research has identified an important latent factor - the \"confidence\" of LLMs - during the self-correction process. Overlooking this factor may cause the models to over-criticize themselves, resulting in unreliable conclusions regarding the efficacy of self-correction. We have experimentally observed that LLMs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12563","kind":"arxiv","version":3},"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/2402.12563/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":"2402.12563","created_at":"2026-07-05T08:18:05.506999+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.12563v3","created_at":"2026-07-05T08:18:05.506999+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12563","created_at":"2026-07-05T08:18:05.506999+00:00"},{"alias_kind":"pith_short_12","alias_value":"FKVGHVNPHFFY","created_at":"2026-07-05T08:18:05.506999+00:00"},{"alias_kind":"pith_short_16","alias_value":"FKVGHVNPHFFYG4EV","created_at":"2026-07-05T08:18:05.506999+00:00"},{"alias_kind":"pith_short_8","alias_value":"FKVGHVNP","created_at":"2026-07-05T08:18:05.506999+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23196","citing_title":"When Does Intrinsic Self-Correction Help? A Task-Sensitive Analysis","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09875","citing_title":"Integrating Local and Global Entropy for Uncertainty Quantification in LLMs","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31455","citing_title":"DRIFT: Decoupled Rollouts and Importance-Weighted Fine-Tuning for Efficient Multi-Turn Optimization","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2509.02547","citing_title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","ref_index":158,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21046","citing_title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","ref_index":211,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26644","citing_title":"When to Vote, When to Rewrite: Disagreement-Guided Strategy Routing for Test-Time Scaling","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22271","citing_title":"How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06805","citing_title":"Cognitive Loop of Thought: Reversible Hierarchical Markov Chain for Efficient Mathematical Reasoning","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FKVGHVNPHFFYG4EVAV4LW7UOQV","json":"https://pith.science/pith/FKVGHVNPHFFYG4EVAV4LW7UOQV.json","graph_json":"https://pith.science/api/pith-number/FKVGHVNPHFFYG4EVAV4LW7UOQV/graph.json","events_json":"https://pith.science/api/pith-number/FKVGHVNPHFFYG4EVAV4LW7UOQV/events.json","paper":"https://pith.science/paper/FKVGHVNP"},"agent_actions":{"view_html":"https://pith.science/pith/FKVGHVNPHFFYG4EVAV4LW7UOQV","download_json":"https://pith.science/pith/FKVGHVNPHFFYG4EVAV4LW7UOQV.json","view_paper":"https://pith.science/paper/FKVGHVNP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.12563&json=true","fetch_graph":"https://pith.science/api/pith-number/FKVGHVNPHFFYG4EVAV4LW7UOQV/graph.json","fetch_events":"https://pith.science/api/pith-number/FKVGHVNPHFFYG4EVAV4LW7UOQV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FKVGHVNPHFFYG4EVAV4LW7UOQV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FKVGHVNPHFFYG4EVAV4LW7UOQV/action/storage_attestation","attest_author":"https://pith.science/pith/FKVGHVNPHFFYG4EVAV4LW7UOQV/action/author_attestation","sign_citation":"https://pith.science/pith/FKVGHVNPHFFYG4EVAV4LW7UOQV/action/citation_signature","submit_replication":"https://pith.science/pith/FKVGHVNPHFFYG4EVAV4LW7UOQV/action/replication_record"}},"created_at":"2026-07-05T08:18:05.506999+00:00","updated_at":"2026-07-05T08:18:05.506999+00:00"}