{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MO7FHALARQ2JLVXJJ4AD5XVHM6","short_pith_number":"pith:MO7FHALA","schema_version":"1.0","canonical_sha256":"63be5381608c3495d6e94f003edea76783189088cc01475bd5e0bd8774dec4ba","source":{"kind":"arxiv","id":"2305.14627","version":2},"attestation_state":"computed","paper":{"title":"Enabling Large Language Models to Generate Text with Citations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Danqi Chen, Howard Yen, Jiatong Yu, Tianyu Gao","submitted_at":"2023-05-24T01:53:49Z","abstract_excerpt":"Large language models (LLMs) have emerged as a widely-used tool for information seeking, but their generated outputs are prone to hallucination. In this work, our aim is to allow LLMs to generate text with citations, improving their factual correctness and verifiability. Existing work mainly relies on commercial search engines and human evaluation, making it challenging to reproduce and compare different modeling approaches. We propose ALCE, the first benchmark for Automatic LLMs' Citation Evaluation. ALCE collects a diverse set of questions and retrieval corpora and requires building end-to-e"},"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":"2305.14627","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T01:53:49Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"b67d26995dc961c243abe48a22846bf30071d2ea72c0e113e757ef1ccd621cbf","abstract_canon_sha256":"26d1f38b9ac0c78cb3f3f9e70de1d4b0fe7e29acb21cca58059e69f2fd3ea44c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:10.464526Z","signature_b64":"7xtcFt71F8JQxU52JjoB3rHbjEIPG+YlNFtaXZSgfDrcEVT6d7u6GDVo08RbPKLtLmNLL9RZOM0476XTCQWZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63be5381608c3495d6e94f003edea76783189088cc01475bd5e0bd8774dec4ba","last_reissued_at":"2026-07-05T07:07:10.464003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:10.464003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enabling Large Language Models to Generate Text with Citations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Danqi Chen, Howard Yen, Jiatong Yu, Tianyu Gao","submitted_at":"2023-05-24T01:53:49Z","abstract_excerpt":"Large language models (LLMs) have emerged as a widely-used tool for information seeking, but their generated outputs are prone to hallucination. In this work, our aim is to allow LLMs to generate text with citations, improving their factual correctness and verifiability. Existing work mainly relies on commercial search engines and human evaluation, making it challenging to reproduce and compare different modeling approaches. We propose ALCE, the first benchmark for Automatic LLMs' Citation Evaluation. ALCE collects a diverse set of questions and retrieval corpora and requires building end-to-e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14627","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/2305.14627/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":"2305.14627","created_at":"2026-07-05T07:07:10.464062+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14627v2","created_at":"2026-07-05T07:07:10.464062+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14627","created_at":"2026-07-05T07:07:10.464062+00:00"},{"alias_kind":"pith_short_12","alias_value":"MO7FHALARQ2J","created_at":"2026-07-05T07:07:10.464062+00:00"},{"alias_kind":"pith_short_16","alias_value":"MO7FHALARQ2JLVXJ","created_at":"2026-07-05T07:07:10.464062+00:00"},{"alias_kind":"pith_short_8","alias_value":"MO7FHALA","created_at":"2026-07-05T07:07:10.464062+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08011","citing_title":"Beware What You Autocomplete: Forensic Attribution of Backdoored Code Completions","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2606.03728","citing_title":"Re-Ranking Through an Attribution Lens for Citation Quality in Legal QA","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28360","citing_title":"Carolina Guide: A Multi-Agent RAG System with Institutional Guardrails for Academic Policy Assistance","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24894","citing_title":"RWGBench: Evaluating Scholarly Positioning in Related Work Generation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2412.14751","citing_title":"Query pipeline optimization for cancer patient question answering systems","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2503.04338","citing_title":"In-depth Analysis of Graph-based RAG in a Unified Framework","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20478","citing_title":"Stage-Audit: Auditable Source-Frontier Discovery for Cross-Wiki Tables","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00505","citing_title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2506.19977","citing_title":"Context Attribution with Multi-Armed Bandit Optimization","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2401.15391","citing_title":"MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2401.18059","citing_title":"RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15109","citing_title":"Why Neighborhoods Matter: Traversal Context and Provenance in Agentic GraphRAG","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2310.11511","citing_title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","ref_index":131,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09012","citing_title":"Re$^2$Math: Benchmarking Theorem Retrieval in Research-Level Mathematics","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00505","citing_title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07012","citing_title":"DTCRS: Dynamic Tree Construction for Recursive Summarization","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15621","citing_title":"Rethinking the Necessity of Adaptive Retrieval-Augmented Generation through the Lens of Adaptive Listwise Ranking","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MO7FHALARQ2JLVXJJ4AD5XVHM6","json":"https://pith.science/pith/MO7FHALARQ2JLVXJJ4AD5XVHM6.json","graph_json":"https://pith.science/api/pith-number/MO7FHALARQ2JLVXJJ4AD5XVHM6/graph.json","events_json":"https://pith.science/api/pith-number/MO7FHALARQ2JLVXJJ4AD5XVHM6/events.json","paper":"https://pith.science/paper/MO7FHALA"},"agent_actions":{"view_html":"https://pith.science/pith/MO7FHALARQ2JLVXJJ4AD5XVHM6","download_json":"https://pith.science/pith/MO7FHALARQ2JLVXJJ4AD5XVHM6.json","view_paper":"https://pith.science/paper/MO7FHALA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14627&json=true","fetch_graph":"https://pith.science/api/pith-number/MO7FHALARQ2JLVXJJ4AD5XVHM6/graph.json","fetch_events":"https://pith.science/api/pith-number/MO7FHALARQ2JLVXJJ4AD5XVHM6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MO7FHALARQ2JLVXJJ4AD5XVHM6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MO7FHALARQ2JLVXJJ4AD5XVHM6/action/storage_attestation","attest_author":"https://pith.science/pith/MO7FHALARQ2JLVXJJ4AD5XVHM6/action/author_attestation","sign_citation":"https://pith.science/pith/MO7FHALARQ2JLVXJJ4AD5XVHM6/action/citation_signature","submit_replication":"https://pith.science/pith/MO7FHALARQ2JLVXJJ4AD5XVHM6/action/replication_record"}},"created_at":"2026-07-05T07:07:10.464062+00:00","updated_at":"2026-07-05T07:07:10.464062+00:00"}