{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DGGEF34DUVTRYHDDWHGP2ZPBQK","short_pith_number":"pith:DGGEF34D","schema_version":"1.0","canonical_sha256":"198c42ef83a5671c1c63b1ccfd65e182a3515f3d7d14e5f17f2f9f8be36c3c94","source":{"kind":"arxiv","id":"2411.11531","version":2},"attestation_state":"computed","paper":{"title":"Addressing Hallucinations in Language Models with Knowledge Graph Embeddings as an Additional Modality","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrey Kuznetsov, Anton Razzhigaev, Elizaveta Goncharova, Viktoriia Chekalina","submitted_at":"2024-11-18T12:40:51Z","abstract_excerpt":"In this paper we present an approach to reduce hallucinations in Large Language Models (LLMs) by incorporating Knowledge Graphs (KGs) as an additional modality. Our method involves transforming input text into a set of KG embeddings and using an adapter to integrate these embeddings into the language model space, without relying on external retrieval processes.\n  To facilitate this, we created WikiEntities, a dataset containing over 3 million Wikipedia texts annotated with entities from Wikidata and their corresponding embeddings from PyTorch-BigGraph. This dataset serves as a valuable resourc"},"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":"2411.11531","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T12:40:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9903b66a1baa6c52620377e1d8d8d3d44ef9d66dba337c1b5be3a6d554f918e2","abstract_canon_sha256":"80eb9304cca758ce99d94e85bcecbc0c2c02b6a44a1d6bff2cf3162bcba78159"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:43.479799Z","signature_b64":"LvxSpQV0XX0Y16ZgQAa0nAchunHVdHir92N2OpYebhw33eKF1DawPIaLq2RG/vbuIX3Jyb14H3PVAwCFeFO6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"198c42ef83a5671c1c63b1ccfd65e182a3515f3d7d14e5f17f2f9f8be36c3c94","last_reissued_at":"2026-07-05T10:00:43.479396Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:43.479396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Addressing Hallucinations in Language Models with Knowledge Graph Embeddings as an Additional Modality","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrey Kuznetsov, Anton Razzhigaev, Elizaveta Goncharova, Viktoriia Chekalina","submitted_at":"2024-11-18T12:40:51Z","abstract_excerpt":"In this paper we present an approach to reduce hallucinations in Large Language Models (LLMs) by incorporating Knowledge Graphs (KGs) as an additional modality. Our method involves transforming input text into a set of KG embeddings and using an adapter to integrate these embeddings into the language model space, without relying on external retrieval processes.\n  To facilitate this, we created WikiEntities, a dataset containing over 3 million Wikipedia texts annotated with entities from Wikidata and their corresponding embeddings from PyTorch-BigGraph. This dataset serves as a valuable resourc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11531","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/2411.11531/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":"2411.11531","created_at":"2026-07-05T10:00:43.479452+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.11531v2","created_at":"2026-07-05T10:00:43.479452+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11531","created_at":"2026-07-05T10:00:43.479452+00:00"},{"alias_kind":"pith_short_12","alias_value":"DGGEF34DUVTR","created_at":"2026-07-05T10:00:43.479452+00:00"},{"alias_kind":"pith_short_16","alias_value":"DGGEF34DUVTRYHDD","created_at":"2026-07-05T10:00:43.479452+00:00"},{"alias_kind":"pith_short_8","alias_value":"DGGEF34D","created_at":"2026-07-05T10:00:43.479452+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.13334","citing_title":"A Survey of Context Engineering for Large Language Models","ref_index":132,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DGGEF34DUVTRYHDDWHGP2ZPBQK","json":"https://pith.science/pith/DGGEF34DUVTRYHDDWHGP2ZPBQK.json","graph_json":"https://pith.science/api/pith-number/DGGEF34DUVTRYHDDWHGP2ZPBQK/graph.json","events_json":"https://pith.science/api/pith-number/DGGEF34DUVTRYHDDWHGP2ZPBQK/events.json","paper":"https://pith.science/paper/DGGEF34D"},"agent_actions":{"view_html":"https://pith.science/pith/DGGEF34DUVTRYHDDWHGP2ZPBQK","download_json":"https://pith.science/pith/DGGEF34DUVTRYHDDWHGP2ZPBQK.json","view_paper":"https://pith.science/paper/DGGEF34D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.11531&json=true","fetch_graph":"https://pith.science/api/pith-number/DGGEF34DUVTRYHDDWHGP2ZPBQK/graph.json","fetch_events":"https://pith.science/api/pith-number/DGGEF34DUVTRYHDDWHGP2ZPBQK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DGGEF34DUVTRYHDDWHGP2ZPBQK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DGGEF34DUVTRYHDDWHGP2ZPBQK/action/storage_attestation","attest_author":"https://pith.science/pith/DGGEF34DUVTRYHDDWHGP2ZPBQK/action/author_attestation","sign_citation":"https://pith.science/pith/DGGEF34DUVTRYHDDWHGP2ZPBQK/action/citation_signature","submit_replication":"https://pith.science/pith/DGGEF34DUVTRYHDDWHGP2ZPBQK/action/replication_record"}},"created_at":"2026-07-05T10:00:43.479452+00:00","updated_at":"2026-07-05T10:00:43.479452+00:00"}