{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PT4Y6HGAZMHNPNEWKHV7KD2SCP","short_pith_number":"pith:PT4Y6HGA","schema_version":"1.0","canonical_sha256":"7cf98f1cc0cb0ed7b49651ebf50f5213c30335fbc700e348a272bdc58cae7d5e","source":{"kind":"arxiv","id":"2302.12813","version":3},"attestation_state":"computed","paper":{"title":"Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"LLM-Augmenter augments black-box models like ChatGPT with external knowledge modules and automated feedback to reduce hallucinations while preserving fluency.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Baolin Peng, Hao Cheng, Jianfeng Gao, Lars Liden, Michel Galley, Pengcheng He, Qiuyuan Huang, Weizhu Chen, Yu Hu, Yujia Xie, Zhou Yu","submitted_at":"2023-02-24T18:48:43Z","abstract_excerpt":"Large language models (LLMs), such as ChatGPT, are able to generate human-like, fluent responses for many downstream tasks, e.g., task-oriented dialog and question answering. However, applying LLMs to real-world, mission-critical applications remains challenging mainly due to their tendency to generate hallucinations and their inability to use external knowledge. This paper proposes a LLM-Augmenter system, which augments a black-box LLM with a set of plug-and-play modules. Our system makes the LLM generate responses grounded in external knowledge, e.g., stored in task-specific databases. It al"},"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":true},"canonical_record":{"source":{"id":"2302.12813","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-24T18:48:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e76cb4409e5a4f1b7c262877010a2f67881ae0ff3f7f7c5dbae51b8faca4f459","abstract_canon_sha256":"15e69d9cba5b57e7fccaf618e490af2ec4523001c530954e7fb5af1e364bf0c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:14.429920Z","signature_b64":"t5QfxXBwMHvRFXB2DzUxeidx0UCLN4ABq20cQb6ZBNq6tF71Lb/ezeCaLTgZMNzW/3QpmlkHxtDzDdf69EoDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cf98f1cc0cb0ed7b49651ebf50f5213c30335fbc700e348a272bdc58cae7d5e","last_reissued_at":"2026-05-17T23:38:14.429196Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:14.429196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"LLM-Augmenter augments black-box models like ChatGPT with external knowledge modules and automated feedback to reduce hallucinations while preserving fluency.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Baolin Peng, Hao Cheng, Jianfeng Gao, Lars Liden, Michel Galley, Pengcheng He, Qiuyuan Huang, Weizhu Chen, Yu Hu, Yujia Xie, Zhou Yu","submitted_at":"2023-02-24T18:48:43Z","abstract_excerpt":"Large language models (LLMs), such as ChatGPT, are able to generate human-like, fluent responses for many downstream tasks, e.g., task-oriented dialog and question answering. However, applying LLMs to real-world, mission-critical applications remains challenging mainly due to their tendency to generate hallucinations and their inability to use external knowledge. This paper proposes a LLM-Augmenter system, which augments a black-box LLM with a set of plug-and-play modules. Our system makes the LLM generate responses grounded in external knowledge, e.g., stored in task-specific databases. It al"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"LLM-Augmenter significantly reduces ChatGPT's hallucinations without sacrificing the fluency and informativeness of its responses.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That utility functions such as factuality scores can reliably detect and guide correction of hallucinations without introducing new errors or degrading response quality.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LLM-Augmenter reduces hallucinations in LLMs like ChatGPT by grounding responses in external knowledge and using automated feedback loops to iteratively revise outputs.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"LLM-Augmenter augments black-box models like ChatGPT with external knowledge modules and automated feedback to reduce hallucinations while preserving fluency.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"6008599ef363fb51d705b05be76bbedb830d302b6294e29ef95c0adbb64ecb56"},"source":{"id":"2302.12813","kind":"arxiv","version":3},"verdict":{"id":"57f018a2-bad6-4d6b-9075-36d0b856329c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T09:56:55.544089Z","strongest_claim":"LLM-Augmenter significantly reduces ChatGPT's hallucinations without sacrificing the fluency and informativeness of its responses.","one_line_summary":"LLM-Augmenter reduces hallucinations in LLMs like ChatGPT by grounding responses in external knowledge and using automated feedback loops to iteratively revise outputs.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That utility functions such as factuality scores can reliably detect and guide correction of hallucinations without introducing new errors or degrading response quality.","pith_extraction_headline":"LLM-Augmenter augments black-box models like ChatGPT with external knowledge modules and automated feedback to reduce hallucinations while preserving fluency."},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d242727f8af11c7ba870a1ddea1a8d1ede51b6906cbd44015231a29e4d082674"},"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":"2302.12813","created_at":"2026-05-17T23:38:14.429304+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.12813v3","created_at":"2026-05-17T23:38:14.429304+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.12813","created_at":"2026-05-17T23:38:14.429304+00:00"},{"alias_kind":"pith_short_12","alias_value":"PT4Y6HGAZMHN","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"PT4Y6HGAZMHNPNEW","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"PT4Y6HGA","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":26,"internal_anchor_count":26,"sample":[{"citing_arxiv_id":"2312.11805","citing_title":"Gemini: A Family of Highly Capable Multimodal Models","ref_index":74,"is_internal_anchor":true},{"citing_arxiv_id":"2407.20240","citing_title":"Social and Ethical Risks Posed by General-Purpose LLMs for Settling Newcomers in Canada","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2409.10102","citing_title":"Trustworthiness in Retrieval-Augmented Generation Systems: A Survey","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2410.20791","citing_title":"From Cool Demos to Production-Ready FMware: Core Challenges and a Technology Roadmap","ref_index":82,"is_internal_anchor":true},{"citing_arxiv_id":"2509.22202","citing_title":"Library Hallucinations in LLM-Generated Code: A Risk Analysis Grounded in Developer Queries","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2506.04565","citing_title":"From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems","ref_index":130,"is_internal_anchor":true},{"citing_arxiv_id":"2401.03568","citing_title":"Agent AI: Surveying the Horizons of Multimodal Interaction","ref_index":177,"is_internal_anchor":true},{"citing_arxiv_id":"2309.11495","citing_title":"Chain-of-Verification Reduces Hallucination in Large Language Models","ref_index":108,"is_internal_anchor":true},{"citing_arxiv_id":"2406.15927","citing_title":"Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs","ref_index":57,"is_internal_anchor":true},{"citing_arxiv_id":"2401.05459","citing_title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","ref_index":228,"is_internal_anchor":true},{"citing_arxiv_id":"2309.05922","citing_title":"A Survey of Hallucination in Large Foundation Models","ref_index":139,"is_internal_anchor":true},{"citing_arxiv_id":"2602.01386","citing_title":"\"If You're Very Clever, No One Knows You've Used It\": The Social Dynamics of Developing Generative AI Literacy in the Workplace","ref_index":86,"is_internal_anchor":true},{"citing_arxiv_id":"2304.13734","citing_title":"The Internal State of an LLM Knows When It's Lying","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2309.17421","citing_title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","ref_index":104,"is_internal_anchor":true},{"citing_arxiv_id":"2401.11817","citing_title":"Hallucination is Inevitable: An Innate Limitation of Large Language Models","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2603.12564","citing_title":"Sell Me This Stock: Unsafe Recommendation Drift in LLM Agents","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12813","citing_title":"REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2304.03277","citing_title":"Instruction Tuning with GPT-4","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2603.29908","citing_title":"C-TRAIL: A Commonsense World Framework for Trajectory Planning in Autonomous Driving","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2305.11738","citing_title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2503.13657","citing_title":"Why Do Multi-Agent LLM Systems Fail?","ref_index":72,"is_internal_anchor":true},{"citing_arxiv_id":"2402.06196","citing_title":"Large Language Models: A Survey","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2309.07864","citing_title":"The Rise and Potential of Large Language Model Based Agents: A Survey","ref_index":104,"is_internal_anchor":true},{"citing_arxiv_id":"2303.17651","citing_title":"Self-Refine: Iterative Refinement with Self-Feedback","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2403.07974","citing_title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","ref_index":294,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PT4Y6HGAZMHNPNEWKHV7KD2SCP","json":"https://pith.science/pith/PT4Y6HGAZMHNPNEWKHV7KD2SCP.json","graph_json":"https://pith.science/api/pith-number/PT4Y6HGAZMHNPNEWKHV7KD2SCP/graph.json","events_json":"https://pith.science/api/pith-number/PT4Y6HGAZMHNPNEWKHV7KD2SCP/events.json","paper":"https://pith.science/paper/PT4Y6HGA"},"agent_actions":{"view_html":"https://pith.science/pith/PT4Y6HGAZMHNPNEWKHV7KD2SCP","download_json":"https://pith.science/pith/PT4Y6HGAZMHNPNEWKHV7KD2SCP.json","view_paper":"https://pith.science/paper/PT4Y6HGA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.12813&json=true","fetch_graph":"https://pith.science/api/pith-number/PT4Y6HGAZMHNPNEWKHV7KD2SCP/graph.json","fetch_events":"https://pith.science/api/pith-number/PT4Y6HGAZMHNPNEWKHV7KD2SCP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PT4Y6HGAZMHNPNEWKHV7KD2SCP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PT4Y6HGAZMHNPNEWKHV7KD2SCP/action/storage_attestation","attest_author":"https://pith.science/pith/PT4Y6HGAZMHNPNEWKHV7KD2SCP/action/author_attestation","sign_citation":"https://pith.science/pith/PT4Y6HGAZMHNPNEWKHV7KD2SCP/action/citation_signature","submit_replication":"https://pith.science/pith/PT4Y6HGAZMHNPNEWKHV7KD2SCP/action/replication_record"}},"created_at":"2026-05-17T23:38:14.429304+00:00","updated_at":"2026-05-17T23:38:14.429304+00:00"}