{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FK5T7OA5AKBZT5Y6FNP4FELY2K","short_pith_number":"pith:FK5T7OA5","schema_version":"1.0","canonical_sha256":"2abb3fb81d028399f71e2b5fc29178d284d0ac946eb0d428505c2212bbe3570a","source":{"kind":"arxiv","id":"2305.18846","version":1},"attestation_state":"computed","paper":{"title":"Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jinheon Baek, Jin Myung Kwak, Minki Kang, Sung Ju Hwang","submitted_at":"2023-05-30T08:36:45Z","abstract_excerpt":"Language models have achieved impressive performances on dialogue generation tasks. However, when generating responses for a conversation that requires factual knowledge, they are far from perfect, due to an absence of mechanisms to retrieve, encode, and reflect the knowledge in the generated responses. Some knowledge-grounded dialogue generation methods tackle this problem by leveraging facts from Knowledge Graphs (KGs); however, they do not guarantee that the model utilizes a relevant piece of knowledge from the KG. To overcome this limitation, we propose SUbgraph Retrieval-augmented GEnerat"},"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":"2305.18846","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-30T08:36:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a5522e0b3aefbb79980df99ea0bef9887925b9d9da9776b1c7f1b56c27499cde","abstract_canon_sha256":"6674c75badd40a81583b5f92a86fc05104e66846ab7877f4c68ddff7f0b206b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:33.815747Z","signature_b64":"CmwnDIEiPEkL7n23GbZNSDpvio/0435cr3ONTxOmixokJa3S3kd7MHSefK2qjYf4FtQmDM4su0u9sa6tMBVRBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2abb3fb81d028399f71e2b5fc29178d284d0ac946eb0d428505c2212bbe3570a","last_reissued_at":"2026-07-05T06:15:33.815270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:33.815270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jinheon Baek, Jin Myung Kwak, Minki Kang, Sung Ju Hwang","submitted_at":"2023-05-30T08:36:45Z","abstract_excerpt":"Language models have achieved impressive performances on dialogue generation tasks. However, when generating responses for a conversation that requires factual knowledge, they are far from perfect, due to an absence of mechanisms to retrieve, encode, and reflect the knowledge in the generated responses. Some knowledge-grounded dialogue generation methods tackle this problem by leveraging facts from Knowledge Graphs (KGs); however, they do not guarantee that the model utilizes a relevant piece of knowledge from the KG. To overcome this limitation, we propose SUbgraph Retrieval-augmented GEnerat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18846","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/2305.18846/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":"2305.18846","created_at":"2026-07-05T06:15:33.815338+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18846v1","created_at":"2026-07-05T06:15:33.815338+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18846","created_at":"2026-07-05T06:15:33.815338+00:00"},{"alias_kind":"pith_short_12","alias_value":"FK5T7OA5AKBZ","created_at":"2026-07-05T06:15:33.815338+00:00"},{"alias_kind":"pith_short_16","alias_value":"FK5T7OA5AKBZT5Y6","created_at":"2026-07-05T06:15:33.815338+00:00"},{"alias_kind":"pith_short_8","alias_value":"FK5T7OA5","created_at":"2026-07-05T06:15:33.815338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2404.10981","citing_title":"A Survey on Retrieval-Augmented Text Generation for Large Language Models","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2404.16130","citing_title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17458","citing_title":"EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval","ref_index":91,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FK5T7OA5AKBZT5Y6FNP4FELY2K","json":"https://pith.science/pith/FK5T7OA5AKBZT5Y6FNP4FELY2K.json","graph_json":"https://pith.science/api/pith-number/FK5T7OA5AKBZT5Y6FNP4FELY2K/graph.json","events_json":"https://pith.science/api/pith-number/FK5T7OA5AKBZT5Y6FNP4FELY2K/events.json","paper":"https://pith.science/paper/FK5T7OA5"},"agent_actions":{"view_html":"https://pith.science/pith/FK5T7OA5AKBZT5Y6FNP4FELY2K","download_json":"https://pith.science/pith/FK5T7OA5AKBZT5Y6FNP4FELY2K.json","view_paper":"https://pith.science/paper/FK5T7OA5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18846&json=true","fetch_graph":"https://pith.science/api/pith-number/FK5T7OA5AKBZT5Y6FNP4FELY2K/graph.json","fetch_events":"https://pith.science/api/pith-number/FK5T7OA5AKBZT5Y6FNP4FELY2K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FK5T7OA5AKBZT5Y6FNP4FELY2K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FK5T7OA5AKBZT5Y6FNP4FELY2K/action/storage_attestation","attest_author":"https://pith.science/pith/FK5T7OA5AKBZT5Y6FNP4FELY2K/action/author_attestation","sign_citation":"https://pith.science/pith/FK5T7OA5AKBZT5Y6FNP4FELY2K/action/citation_signature","submit_replication":"https://pith.science/pith/FK5T7OA5AKBZT5Y6FNP4FELY2K/action/replication_record"}},"created_at":"2026-07-05T06:15:33.815338+00:00","updated_at":"2026-07-05T06:15:33.815338+00:00"}