{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ACTBH7HEC2PP5QDPSJZAK7Y47C","short_pith_number":"pith:ACTBH7HE","schema_version":"1.0","canonical_sha256":"00a613fce4169efec06f9272057f1cf8b69d7f458f82e700e7fbe758562787d5","source":{"kind":"arxiv","id":"2410.09699","version":1},"attestation_state":"computed","paper":{"title":"Honest AI: Fine-Tuning \"Small\" Language Models to Say \"I Don't Know\", and Reducing Hallucination in RAG","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Li Wang, Qi Tang, Wei Wu, Xinxi Chen, Yiyao Liu","submitted_at":"2024-10-13T02:34:47Z","abstract_excerpt":"Hallucination is a key roadblock for applications of Large Language Models (LLMs), particularly for enterprise applications that are sensitive to information accuracy. To address this issue, two general approaches have been explored: Retrieval-Augmented Generation (RAG) to supply LLMs with updated information as context, and fine-tuning the LLMs with new information and desired output styles. In this paper, we propose Honest AI: a novel strategy to fine-tune \"small\" language models to say \"I don't know\" to reduce hallucination, along with several alternative RAG approaches. The solution ranked"},"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":"2410.09699","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-13T02:34:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3e6d011896dfda7429135472275c179d48113afdbf7f1c99a74650022fd5837e","abstract_canon_sha256":"05778bb69622d5ff4e0c762a31b1a89a06130c8cd981f2705f46cbd20ea7ff6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:42.828235Z","signature_b64":"cFmJVh0DUeKb2ckvsD5GHU6MhNNd1cmFtKaFtE+B4IqxAmF/oYHHp9uuCqqXF3UiPv0u8eRhOovfIRQ+rdbdBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00a613fce4169efec06f9272057f1cf8b69d7f458f82e700e7fbe758562787d5","last_reissued_at":"2026-07-05T09:19:42.827702Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:42.827702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Honest AI: Fine-Tuning \"Small\" Language Models to Say \"I Don't Know\", and Reducing Hallucination in RAG","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Li Wang, Qi Tang, Wei Wu, Xinxi Chen, Yiyao Liu","submitted_at":"2024-10-13T02:34:47Z","abstract_excerpt":"Hallucination is a key roadblock for applications of Large Language Models (LLMs), particularly for enterprise applications that are sensitive to information accuracy. To address this issue, two general approaches have been explored: Retrieval-Augmented Generation (RAG) to supply LLMs with updated information as context, and fine-tuning the LLMs with new information and desired output styles. In this paper, we propose Honest AI: a novel strategy to fine-tune \"small\" language models to say \"I don't know\" to reduce hallucination, along with several alternative RAG approaches. The solution ranked"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09699","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/2410.09699/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":"2410.09699","created_at":"2026-07-05T09:19:42.827762+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.09699v1","created_at":"2026-07-05T09:19:42.827762+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09699","created_at":"2026-07-05T09:19:42.827762+00:00"},{"alias_kind":"pith_short_12","alias_value":"ACTBH7HEC2PP","created_at":"2026-07-05T09:19:42.827762+00:00"},{"alias_kind":"pith_short_16","alias_value":"ACTBH7HEC2PP5QDP","created_at":"2026-07-05T09:19:42.827762+00:00"},{"alias_kind":"pith_short_8","alias_value":"ACTBH7HE","created_at":"2026-07-05T09:19:42.827762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.05554","citing_title":"LLMQuoter: Enhancing RAG Capabilities Through Efficient Quote Extraction From Large Contexts","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ACTBH7HEC2PP5QDPSJZAK7Y47C","json":"https://pith.science/pith/ACTBH7HEC2PP5QDPSJZAK7Y47C.json","graph_json":"https://pith.science/api/pith-number/ACTBH7HEC2PP5QDPSJZAK7Y47C/graph.json","events_json":"https://pith.science/api/pith-number/ACTBH7HEC2PP5QDPSJZAK7Y47C/events.json","paper":"https://pith.science/paper/ACTBH7HE"},"agent_actions":{"view_html":"https://pith.science/pith/ACTBH7HEC2PP5QDPSJZAK7Y47C","download_json":"https://pith.science/pith/ACTBH7HEC2PP5QDPSJZAK7Y47C.json","view_paper":"https://pith.science/paper/ACTBH7HE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.09699&json=true","fetch_graph":"https://pith.science/api/pith-number/ACTBH7HEC2PP5QDPSJZAK7Y47C/graph.json","fetch_events":"https://pith.science/api/pith-number/ACTBH7HEC2PP5QDPSJZAK7Y47C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ACTBH7HEC2PP5QDPSJZAK7Y47C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ACTBH7HEC2PP5QDPSJZAK7Y47C/action/storage_attestation","attest_author":"https://pith.science/pith/ACTBH7HEC2PP5QDPSJZAK7Y47C/action/author_attestation","sign_citation":"https://pith.science/pith/ACTBH7HEC2PP5QDPSJZAK7Y47C/action/citation_signature","submit_replication":"https://pith.science/pith/ACTBH7HEC2PP5QDPSJZAK7Y47C/action/replication_record"}},"created_at":"2026-07-05T09:19:42.827762+00:00","updated_at":"2026-07-05T09:19:42.827762+00:00"}