{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OYPT5ZJONNDXIQO62VBEASV37H","short_pith_number":"pith:OYPT5ZJO","schema_version":"1.0","canonical_sha256":"761f3ee52e6b477441ded542404abbf9f0a6802b205431acfbd294a7d0d213c8","source":{"kind":"arxiv","id":"2307.03987","version":2},"attestation_state":"computed","paper":{"title":"A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dong Yu, Hongming Zhang, Jianshu Chen, Neeraj Varshney, Wenlin Yao","submitted_at":"2023-07-08T14:25:57Z","abstract_excerpt":"Recently developed large language models have achieved remarkable success in generating fluent and coherent text. However, these models often tend to 'hallucinate' which critically hampers their reliability. In this work, we address this crucial problem and propose an approach that actively detects and mitigates hallucinations during the generation process. Specifically, we first identify the candidates of potential hallucination leveraging the model's logit output values, check their correctness through a validation procedure, mitigate the detected hallucinations, and then continue with the g"},"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":"2307.03987","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-08T14:25:57Z","cross_cats_sorted":[],"title_canon_sha256":"bf6ec04769198a4286392b87e5bca23e555a34d6e375f665dd698c453383a92a","abstract_canon_sha256":"20e94c1b6eebfa8e034c30137f5e6a508bc3161c7e040b490759027dc2532a98"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:40:35.225229Z","signature_b64":"9+77HbHPc/TBvlJCZ+DvGG+OIbYJ9UlFFJD9J/Z07WLcyfhp2YgSqm+2w7NnMLdpR9XSbAQWCFQfflNPFFcODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"761f3ee52e6b477441ded542404abbf9f0a6802b205431acfbd294a7d0d213c8","last_reissued_at":"2026-07-05T06:40:35.224729Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:40:35.224729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dong Yu, Hongming Zhang, Jianshu Chen, Neeraj Varshney, Wenlin Yao","submitted_at":"2023-07-08T14:25:57Z","abstract_excerpt":"Recently developed large language models have achieved remarkable success in generating fluent and coherent text. However, these models often tend to 'hallucinate' which critically hampers their reliability. In this work, we address this crucial problem and propose an approach that actively detects and mitigates hallucinations during the generation process. Specifically, we first identify the candidates of potential hallucination leveraging the model's logit output values, check their correctness through a validation procedure, mitigate the detected hallucinations, and then continue with the g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.03987","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/2307.03987/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":"2307.03987","created_at":"2026-07-05T06:40:35.224789+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.03987v2","created_at":"2026-07-05T06:40:35.224789+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.03987","created_at":"2026-07-05T06:40:35.224789+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYPT5ZJONNDX","created_at":"2026-07-05T06:40:35.224789+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYPT5ZJONNDXIQO6","created_at":"2026-07-05T06:40:35.224789+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYPT5ZJO","created_at":"2026-07-05T06:40:35.224789+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04612","citing_title":"Hybrid Adversarial Defence for Natural Language Understanding Tasks","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01434","citing_title":"DrugClaw and DrugAudit: A Primary-Source-Grounded Agent and Authority-Aware Benchmark for Drug-Information Question Answering","ref_index":113,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24919","citing_title":"MultiHaluDet: Multilingual Hallucination Detection via LLM Hidden State Probing","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29090","citing_title":"AB-RAG: Adaptive Budgeted Retrieval-Augmented Generation for Reliable Question Answering","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28264","citing_title":"Entropy Distribution as a Fingerprint for Hallucinations in Generative Models","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02443","citing_title":"HalluScan: A Systematic Benchmark for Detecting and Mitigating Hallucinations in Instruction-Following LLMs","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2603.17839","citing_title":"How do LLMs Compute Verbal Confidence","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20591","citing_title":"Do No Harm? Hallucination and Actor-Level Abuse in Web-Deployed Medical Large Language Models","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2506.13351","citing_title":"Direct Reasoning Optimization: Token-Level Reasoning Reflectivity Meets Rubric Gates for Unverifiable Tasks","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2507.20546","citing_title":"Enhancing Hallucination Detection via Future Context","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2508.18473","citing_title":"Principled Detection of Hallucinations in Large Language Models via Multiple Testing","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2309.11495","citing_title":"Chain-of-Verification Reduces Hallucination in Large Language Models","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2406.15927","citing_title":"Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2309.05922","citing_title":"A Survey of Hallucination in Large Foundation Models","ref_index":144,"is_internal_anchor":false},{"citing_arxiv_id":"2404.18416","citing_title":"Capabilities of Gemini Models in Medicine","ref_index":273,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13068","citing_title":"Detection Without Correction: A Robust Asymmetry in Activation-Based Hallucination Probing","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06522","citing_title":"Agentic AIs Are the Missing Paradigm for Out-of-Distribution Generalization in Foundation Models","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12548","citing_title":"DeepSeek Robustness Against Semantic-Character Dual-Space Mutated Prompt Injection","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06714","citing_title":"Steering the Verifiability of Multimodal AI Hallucinations","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02443","citing_title":"HalluScan: A Systematic Benchmark for Detecting and Mitigating Hallucinations in Instruction-Following LLMs","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OYPT5ZJONNDXIQO62VBEASV37H","json":"https://pith.science/pith/OYPT5ZJONNDXIQO62VBEASV37H.json","graph_json":"https://pith.science/api/pith-number/OYPT5ZJONNDXIQO62VBEASV37H/graph.json","events_json":"https://pith.science/api/pith-number/OYPT5ZJONNDXIQO62VBEASV37H/events.json","paper":"https://pith.science/paper/OYPT5ZJO"},"agent_actions":{"view_html":"https://pith.science/pith/OYPT5ZJONNDXIQO62VBEASV37H","download_json":"https://pith.science/pith/OYPT5ZJONNDXIQO62VBEASV37H.json","view_paper":"https://pith.science/paper/OYPT5ZJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.03987&json=true","fetch_graph":"https://pith.science/api/pith-number/OYPT5ZJONNDXIQO62VBEASV37H/graph.json","fetch_events":"https://pith.science/api/pith-number/OYPT5ZJONNDXIQO62VBEASV37H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYPT5ZJONNDXIQO62VBEASV37H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYPT5ZJONNDXIQO62VBEASV37H/action/storage_attestation","attest_author":"https://pith.science/pith/OYPT5ZJONNDXIQO62VBEASV37H/action/author_attestation","sign_citation":"https://pith.science/pith/OYPT5ZJONNDXIQO62VBEASV37H/action/citation_signature","submit_replication":"https://pith.science/pith/OYPT5ZJONNDXIQO62VBEASV37H/action/replication_record"}},"created_at":"2026-07-05T06:40:35.224789+00:00","updated_at":"2026-07-05T06:40:35.224789+00:00"}