{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FK4IFBEX34L6XL7QI4JP7PLWBH","short_pith_number":"pith:FK4IFBEX","schema_version":"1.0","canonical_sha256":"2ab8828497df17ebaff04712ffbd7609e4932afd4d890f7ee97d1d01153398d3","source":{"kind":"arxiv","id":"2405.10121","version":2},"attestation_state":"computed","paper":{"title":"Distilling Implicit Multimodal Knowledge into Large Language Models for Zero-Resource Dialogue Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CL","authors_text":"Bo Xu, Bo Zhang, Hongfei Lin, Hui Ma, Jian Ding, Jian Wang","submitted_at":"2024-05-16T14:21:33Z","abstract_excerpt":"Integrating multimodal knowledge into large language models (LLMs) represents a significant advancement in dialogue generation capabilities. However, the effective incorporation of such knowledge in zero-resource scenarios remains a substantial challenge due to the scarcity of diverse, high-quality dialogue datasets. To address this, we propose the Visual Implicit Knowledge Distillation Framework (VIKDF), an innovative approach aimed at enhancing LLMs for enriched dialogue generation in zero-resource contexts by leveraging implicit multimodal knowledge. VIKDF comprises two main stages: knowled"},"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":"2405.10121","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-16T14:21:33Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"4b9944906cf6935bae86f424d75c4e0d4534ebfa5ef3362fd34fc7e5e89ae102","abstract_canon_sha256":"f7b4a0ada42f0a1ba4f62dc7b0ce81043002d13babca524a67ce6d6fb78a60ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:43.924269Z","signature_b64":"Myz/vjCSyE90jZzcMuC/3bAiNlkmvNQEM+goKxTjMObvpjieQUUvBuHY9jw0HT+rG0uWES5A1Liopu8SzdehDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ab8828497df17ebaff04712ffbd7609e4932afd4d890f7ee97d1d01153398d3","last_reissued_at":"2026-07-05T10:09:43.923797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:43.923797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distilling Implicit Multimodal Knowledge into Large Language Models for Zero-Resource Dialogue Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CL","authors_text":"Bo Xu, Bo Zhang, Hongfei Lin, Hui Ma, Jian Ding, Jian Wang","submitted_at":"2024-05-16T14:21:33Z","abstract_excerpt":"Integrating multimodal knowledge into large language models (LLMs) represents a significant advancement in dialogue generation capabilities. However, the effective incorporation of such knowledge in zero-resource scenarios remains a substantial challenge due to the scarcity of diverse, high-quality dialogue datasets. To address this, we propose the Visual Implicit Knowledge Distillation Framework (VIKDF), an innovative approach aimed at enhancing LLMs for enriched dialogue generation in zero-resource contexts by leveraging implicit multimodal knowledge. VIKDF comprises two main stages: knowled"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10121","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/2405.10121/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":"2405.10121","created_at":"2026-07-05T10:09:43.923856+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.10121v2","created_at":"2026-07-05T10:09:43.923856+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10121","created_at":"2026-07-05T10:09:43.923856+00:00"},{"alias_kind":"pith_short_12","alias_value":"FK4IFBEX34L6","created_at":"2026-07-05T10:09:43.923856+00:00"},{"alias_kind":"pith_short_16","alias_value":"FK4IFBEX34L6XL7Q","created_at":"2026-07-05T10:09:43.923856+00:00"},{"alias_kind":"pith_short_8","alias_value":"FK4IFBEX","created_at":"2026-07-05T10:09:43.923856+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08621","citing_title":"EvidenT: An Evidence-Preserving Framework for Iterative System-Level Package Repair","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FK4IFBEX34L6XL7QI4JP7PLWBH","json":"https://pith.science/pith/FK4IFBEX34L6XL7QI4JP7PLWBH.json","graph_json":"https://pith.science/api/pith-number/FK4IFBEX34L6XL7QI4JP7PLWBH/graph.json","events_json":"https://pith.science/api/pith-number/FK4IFBEX34L6XL7QI4JP7PLWBH/events.json","paper":"https://pith.science/paper/FK4IFBEX"},"agent_actions":{"view_html":"https://pith.science/pith/FK4IFBEX34L6XL7QI4JP7PLWBH","download_json":"https://pith.science/pith/FK4IFBEX34L6XL7QI4JP7PLWBH.json","view_paper":"https://pith.science/paper/FK4IFBEX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.10121&json=true","fetch_graph":"https://pith.science/api/pith-number/FK4IFBEX34L6XL7QI4JP7PLWBH/graph.json","fetch_events":"https://pith.science/api/pith-number/FK4IFBEX34L6XL7QI4JP7PLWBH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FK4IFBEX34L6XL7QI4JP7PLWBH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FK4IFBEX34L6XL7QI4JP7PLWBH/action/storage_attestation","attest_author":"https://pith.science/pith/FK4IFBEX34L6XL7QI4JP7PLWBH/action/author_attestation","sign_citation":"https://pith.science/pith/FK4IFBEX34L6XL7QI4JP7PLWBH/action/citation_signature","submit_replication":"https://pith.science/pith/FK4IFBEX34L6XL7QI4JP7PLWBH/action/replication_record"}},"created_at":"2026-07-05T10:09:43.923856+00:00","updated_at":"2026-07-05T10:09:43.923856+00:00"}