{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZWJGTGMEZNALZXYDB4VWDSR326","short_pith_number":"pith:ZWJGTGME","schema_version":"1.0","canonical_sha256":"cd92699984cb40bcdf030f2b61ca3bd7bb1d69347881b859b85dae340fe56f57","source":{"kind":"arxiv","id":"2402.11457","version":2},"attestation_state":"computed","paper":{"title":"When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiafeng Guo, Keping Bi, Shiyu Ni, Xueqi Cheng","submitted_at":"2024-02-18T04:57:19Z","abstract_excerpt":"Large Language Models (LLMs) have been found to have difficulty knowing they do not possess certain knowledge and tend to provide specious answers in such cases. Retrieval Augmentation (RA) has been extensively studied to mitigate LLMs' hallucinations. However, due to the extra overhead and unassured quality of retrieval, it may not be optimal to conduct RA all the time. A straightforward idea is to only conduct retrieval when LLMs are uncertain about a question. This motivates us to enhance the LLMs' ability to perceive their knowledge boundaries to help RA. In this paper, we first quantitati"},"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":"2402.11457","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T04:57:19Z","cross_cats_sorted":[],"title_canon_sha256":"5eb8861c6c1759f1de3c52b2f17131cfabc03a880d976793409cd76ec70f6731","abstract_canon_sha256":"9254c43cc42baae92973a0953f4356ce6ea8da5481f789999da5f657b031db3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:08.858601Z","signature_b64":"sRHWHqzQGZjkg8sb2Bipb6w967tqyI2EzhMaey4fPeWptgmuwPOM/KwQ36vxa9pnbiI0Ku0I3Srl/WOt/pRWCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd92699984cb40bcdf030f2b61ca3bd7bb1d69347881b859b85dae340fe56f57","last_reissued_at":"2026-07-05T08:30:08.858123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:08.858123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiafeng Guo, Keping Bi, Shiyu Ni, Xueqi Cheng","submitted_at":"2024-02-18T04:57:19Z","abstract_excerpt":"Large Language Models (LLMs) have been found to have difficulty knowing they do not possess certain knowledge and tend to provide specious answers in such cases. Retrieval Augmentation (RA) has been extensively studied to mitigate LLMs' hallucinations. However, due to the extra overhead and unassured quality of retrieval, it may not be optimal to conduct RA all the time. A straightforward idea is to only conduct retrieval when LLMs are uncertain about a question. This motivates us to enhance the LLMs' ability to perceive their knowledge boundaries to help RA. In this paper, we first quantitati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11457","kind":"arxiv","version":2},"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/2402.11457/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":"2402.11457","created_at":"2026-07-05T08:30:08.858179+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.11457v2","created_at":"2026-07-05T08:30:08.858179+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11457","created_at":"2026-07-05T08:30:08.858179+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZWJGTGMEZNAL","created_at":"2026-07-05T08:30:08.858179+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZWJGTGMEZNALZXYD","created_at":"2026-07-05T08:30:08.858179+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZWJGTGME","created_at":"2026-07-05T08:30:08.858179+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19950","citing_title":"Confidence Calibration for Multimodal LLMs: An Empirical Study through Medical VQA","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03535","citing_title":"Can LLM Rerankers Predict Their Own Ranking Performance?","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2601.02950","citing_title":"Batch-of-Thought: Cross-Instance Learning for Enhanced LLM Reasoning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17112","citing_title":"Complementing Self-Consistency with Cross-Model Disagreement for Uncertainty Quantification","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZWJGTGMEZNALZXYDB4VWDSR326","json":"https://pith.science/pith/ZWJGTGMEZNALZXYDB4VWDSR326.json","graph_json":"https://pith.science/api/pith-number/ZWJGTGMEZNALZXYDB4VWDSR326/graph.json","events_json":"https://pith.science/api/pith-number/ZWJGTGMEZNALZXYDB4VWDSR326/events.json","paper":"https://pith.science/paper/ZWJGTGME"},"agent_actions":{"view_html":"https://pith.science/pith/ZWJGTGMEZNALZXYDB4VWDSR326","download_json":"https://pith.science/pith/ZWJGTGMEZNALZXYDB4VWDSR326.json","view_paper":"https://pith.science/paper/ZWJGTGME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.11457&json=true","fetch_graph":"https://pith.science/api/pith-number/ZWJGTGMEZNALZXYDB4VWDSR326/graph.json","fetch_events":"https://pith.science/api/pith-number/ZWJGTGMEZNALZXYDB4VWDSR326/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZWJGTGMEZNALZXYDB4VWDSR326/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZWJGTGMEZNALZXYDB4VWDSR326/action/storage_attestation","attest_author":"https://pith.science/pith/ZWJGTGMEZNALZXYDB4VWDSR326/action/author_attestation","sign_citation":"https://pith.science/pith/ZWJGTGMEZNALZXYDB4VWDSR326/action/citation_signature","submit_replication":"https://pith.science/pith/ZWJGTGMEZNALZXYDB4VWDSR326/action/replication_record"}},"created_at":"2026-07-05T08:30:08.858179+00:00","updated_at":"2026-07-05T08:30:08.858179+00:00"}