{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MWEIXSSMZIAKL7YMHB6R232Z5M","short_pith_number":"pith:MWEIXSSM","schema_version":"1.0","canonical_sha256":"65888bca4cca00a5ff0c387d1d6f59eb2279adba9788307189355b751d5fd2cf","source":{"kind":"arxiv","id":"2502.10708","version":2},"attestation_state":"computed","paper":{"title":"Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Yan, Miao Fang, Mingzhe Li, Rui Yan, Xiuying Chen, Yuhan Liu, Zirui Song","submitted_at":"2025-02-15T07:43:43Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable success in various tasks such as natural language understanding, text summarization, and machine translation. However, their general-purpose nature often limits their effectiveness in domain-specific applications that require specialized knowledge, such as healthcare, chemistry, or legal analysis. To address this, researchers have explored diverse methods to enhance LLMs by integrating domain-specific knowledge. In this survey, we provide a comprehensive overview of these methods, which we categorize into four key approaches: dynamic kn"},"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":"2502.10708","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-15T07:43:43Z","cross_cats_sorted":[],"title_canon_sha256":"c60151b9c1cdafe9bd1278e684b7239f70f72ddff1cc5d043dc5a14a7451a419","abstract_canon_sha256":"91398a4448d6b037a36435e51a5f4de74f74cdd08fc291dc54a639158e38acf6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:57.699328Z","signature_b64":"iCXtC3uxTaDf6eQ1lBtkYCjftUqJ84uYc2wYNfrBPscm8YykPFIQonbxy7ThSP0ThGAUam+LIOxNDfAgM9unDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65888bca4cca00a5ff0c387d1d6f59eb2279adba9788307189355b751d5fd2cf","last_reissued_at":"2026-07-05T12:01:57.698798Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:57.698798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Yan, Miao Fang, Mingzhe Li, Rui Yan, Xiuying Chen, Yuhan Liu, Zirui Song","submitted_at":"2025-02-15T07:43:43Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable success in various tasks such as natural language understanding, text summarization, and machine translation. However, their general-purpose nature often limits their effectiveness in domain-specific applications that require specialized knowledge, such as healthcare, chemistry, or legal analysis. To address this, researchers have explored diverse methods to enhance LLMs by integrating domain-specific knowledge. In this survey, we provide a comprehensive overview of these methods, which we categorize into four key approaches: dynamic kn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10708","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/2502.10708/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":"2502.10708","created_at":"2026-07-05T12:01:57.698860+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.10708v2","created_at":"2026-07-05T12:01:57.698860+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10708","created_at":"2026-07-05T12:01:57.698860+00:00"},{"alias_kind":"pith_short_12","alias_value":"MWEIXSSMZIAK","created_at":"2026-07-05T12:01:57.698860+00:00"},{"alias_kind":"pith_short_16","alias_value":"MWEIXSSMZIAKL7YM","created_at":"2026-07-05T12:01:57.698860+00:00"},{"alias_kind":"pith_short_8","alias_value":"MWEIXSSM","created_at":"2026-07-05T12:01:57.698860+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20571","citing_title":"Less is More: Lightweight Prompt Compression for Question Answering Applications on Edge Devices","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2503.08223","citing_title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","ref_index":105,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18025","citing_title":"TeleCom-Bench: How Far Are Large Language Models from Industrial Telecommunication Applications?","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24276","citing_title":"G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledge","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19820","citing_title":"KnowPilot: Your Knowledge-Driven Copilot for Domain Tasks","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MWEIXSSMZIAKL7YMHB6R232Z5M","json":"https://pith.science/pith/MWEIXSSMZIAKL7YMHB6R232Z5M.json","graph_json":"https://pith.science/api/pith-number/MWEIXSSMZIAKL7YMHB6R232Z5M/graph.json","events_json":"https://pith.science/api/pith-number/MWEIXSSMZIAKL7YMHB6R232Z5M/events.json","paper":"https://pith.science/paper/MWEIXSSM"},"agent_actions":{"view_html":"https://pith.science/pith/MWEIXSSMZIAKL7YMHB6R232Z5M","download_json":"https://pith.science/pith/MWEIXSSMZIAKL7YMHB6R232Z5M.json","view_paper":"https://pith.science/paper/MWEIXSSM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.10708&json=true","fetch_graph":"https://pith.science/api/pith-number/MWEIXSSMZIAKL7YMHB6R232Z5M/graph.json","fetch_events":"https://pith.science/api/pith-number/MWEIXSSMZIAKL7YMHB6R232Z5M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MWEIXSSMZIAKL7YMHB6R232Z5M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MWEIXSSMZIAKL7YMHB6R232Z5M/action/storage_attestation","attest_author":"https://pith.science/pith/MWEIXSSMZIAKL7YMHB6R232Z5M/action/author_attestation","sign_citation":"https://pith.science/pith/MWEIXSSMZIAKL7YMHB6R232Z5M/action/citation_signature","submit_replication":"https://pith.science/pith/MWEIXSSMZIAKL7YMHB6R232Z5M/action/replication_record"}},"created_at":"2026-07-05T12:01:57.698860+00:00","updated_at":"2026-07-05T12:01:57.698860+00:00"}