{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OPDZ5RTSRPIRPVAZ47NTD7DXC4","short_pith_number":"pith:OPDZ5RTS","schema_version":"1.0","canonical_sha256":"73c79ec6728bd117d419e7db31fc7717105ceccefc5bddce0749881815e398c9","source":{"kind":"arxiv","id":"2305.14292","version":2},"attestation_state":"computed","paper":{"title":"WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Heidi C. Zhang, Monica S. Lam, Sina J. Semnani, Violet Z. Yao","submitted_at":"2023-05-23T17:37:36Z","abstract_excerpt":"This paper presents the first few-shot LLM-based chatbot that almost never hallucinates and has high conversationality and low latency. WikiChat is grounded on the English Wikipedia, the largest curated free-text corpus.\n  WikiChat generates a response from an LLM, retains only the grounded facts, and combines them with additional information it retrieves from the corpus to form factual and engaging responses. We distill WikiChat based on GPT-4 into a 7B-parameter LLaMA model with minimal loss of quality, to significantly improve its latency, cost and privacy, and facilitate research and deplo"},"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":"2305.14292","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T17:37:36Z","cross_cats_sorted":[],"title_canon_sha256":"69863e2c810b536624480360b8b6c557266f1e1fe1206adc2710aa23a1ba4cb4","abstract_canon_sha256":"0e69cc386b231428fff138ba884f61561a7173164a693ab3e99556559f6108b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:34.795076Z","signature_b64":"mUVkDrVpAKmftlbIW6Uk2OxDfUc8rYjHHoucAuK1lMTTwKoWfO2W2CEY/w5WoSZie8bXRrQHSiHcUYFbYf4wBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73c79ec6728bd117d419e7db31fc7717105ceccefc5bddce0749881815e398c9","last_reissued_at":"2026-07-05T08:19:34.794453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:34.794453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Heidi C. Zhang, Monica S. Lam, Sina J. Semnani, Violet Z. Yao","submitted_at":"2023-05-23T17:37:36Z","abstract_excerpt":"This paper presents the first few-shot LLM-based chatbot that almost never hallucinates and has high conversationality and low latency. WikiChat is grounded on the English Wikipedia, the largest curated free-text corpus.\n  WikiChat generates a response from an LLM, retains only the grounded facts, and combines them with additional information it retrieves from the corpus to form factual and engaging responses. We distill WikiChat based on GPT-4 into a 7B-parameter LLaMA model with minimal loss of quality, to significantly improve its latency, cost and privacy, and facilitate research and deplo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14292","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/2305.14292/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":"2305.14292","created_at":"2026-07-05T08:19:34.794539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14292v2","created_at":"2026-07-05T08:19:34.794539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14292","created_at":"2026-07-05T08:19:34.794539+00:00"},{"alias_kind":"pith_short_12","alias_value":"OPDZ5RTSRPIR","created_at":"2026-07-05T08:19:34.794539+00:00"},{"alias_kind":"pith_short_16","alias_value":"OPDZ5RTSRPIRPVAZ","created_at":"2026-07-05T08:19:34.794539+00:00"},{"alias_kind":"pith_short_8","alias_value":"OPDZ5RTS","created_at":"2026-07-05T08:19:34.794539+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24627","citing_title":"The Warrant Gap: Claim-Conditioned Re-scoring for Fact-Checking","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07548","citing_title":"Evaluating Advanced Prompting on Gemini Flash for Multi-Hop Biomedical QA","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2506.04390","citing_title":"Through the Stealth Lens: Attention-Aware Defenses Against Poisoning in RAG","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2504.10166","citing_title":"Fact-Checking with Contextual Narratives: Leveraging Retrieval-Augmented LLMs for Social Media Analysis","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2410.10594","citing_title":"VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OPDZ5RTSRPIRPVAZ47NTD7DXC4","json":"https://pith.science/pith/OPDZ5RTSRPIRPVAZ47NTD7DXC4.json","graph_json":"https://pith.science/api/pith-number/OPDZ5RTSRPIRPVAZ47NTD7DXC4/graph.json","events_json":"https://pith.science/api/pith-number/OPDZ5RTSRPIRPVAZ47NTD7DXC4/events.json","paper":"https://pith.science/paper/OPDZ5RTS"},"agent_actions":{"view_html":"https://pith.science/pith/OPDZ5RTSRPIRPVAZ47NTD7DXC4","download_json":"https://pith.science/pith/OPDZ5RTSRPIRPVAZ47NTD7DXC4.json","view_paper":"https://pith.science/paper/OPDZ5RTS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14292&json=true","fetch_graph":"https://pith.science/api/pith-number/OPDZ5RTSRPIRPVAZ47NTD7DXC4/graph.json","fetch_events":"https://pith.science/api/pith-number/OPDZ5RTSRPIRPVAZ47NTD7DXC4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OPDZ5RTSRPIRPVAZ47NTD7DXC4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OPDZ5RTSRPIRPVAZ47NTD7DXC4/action/storage_attestation","attest_author":"https://pith.science/pith/OPDZ5RTSRPIRPVAZ47NTD7DXC4/action/author_attestation","sign_citation":"https://pith.science/pith/OPDZ5RTSRPIRPVAZ47NTD7DXC4/action/citation_signature","submit_replication":"https://pith.science/pith/OPDZ5RTSRPIRPVAZ47NTD7DXC4/action/replication_record"}},"created_at":"2026-07-05T08:19:34.794539+00:00","updated_at":"2026-07-05T08:19:34.794539+00:00"}