{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UBTLI5X2XY3XSWG6ZIIX7QLMM6","short_pith_number":"pith:UBTLI5X2","schema_version":"1.0","canonical_sha256":"a066b476fabe377958deca117fc16c67bc6fda9b8f9177727971d9c6d5871c3f","source":{"kind":"arxiv","id":"2305.15062","version":2},"attestation_state":"computed","paper":{"title":"Lawyer LLaMA Technical Report","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chen Zhang, Cong Jiang, Mingxu Tao, Quzhe Huang, Yansong Feng, Zhenwei An, Zhibin Chen, Zirui Wu","submitted_at":"2023-05-24T11:52:07Z","abstract_excerpt":"Large Language Models (LLMs), like LLaMA, have exhibited remarkable performance across various tasks. Nevertheless, when deployed to specific domains such as law or medicine, the models still confront the challenge of a deficiency in domain-specific knowledge and an inadequate capability to leverage that knowledge to resolve domain-related problems. In this paper, we propose a new framework to adapt LLMs to specific domains and build Lawyer LLaMA, a legal domain LLM, based on this framework. Specifically, we inject domain knowledge during the continual training stage and teach the model to lea"},"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":"2305.15062","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T11:52:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6b0fd06c0bbcc20debf5a99e89d7ee0033a71149bdf09e6241784ff9f01137fc","abstract_canon_sha256":"1367c48c03856504b5e9e24515b427c55566d31b05284f1fb88a58dfe974bb1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:44.747004Z","signature_b64":"JjyziydWo9iG4IcZLHIrhGNQY+t38iPcrupvd1I79RztjQAoIkinEzNFhehAVhOKIHz1YO0cfit1JoNUXVN4BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a066b476fabe377958deca117fc16c67bc6fda9b8f9177727971d9c6d5871c3f","last_reissued_at":"2026-07-05T07:00:44.746487Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:44.746487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lawyer LLaMA Technical Report","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chen Zhang, Cong Jiang, Mingxu Tao, Quzhe Huang, Yansong Feng, Zhenwei An, Zhibin Chen, Zirui Wu","submitted_at":"2023-05-24T11:52:07Z","abstract_excerpt":"Large Language Models (LLMs), like LLaMA, have exhibited remarkable performance across various tasks. Nevertheless, when deployed to specific domains such as law or medicine, the models still confront the challenge of a deficiency in domain-specific knowledge and an inadequate capability to leverage that knowledge to resolve domain-related problems. In this paper, we propose a new framework to adapt LLMs to specific domains and build Lawyer LLaMA, a legal domain LLM, based on this framework. Specifically, we inject domain knowledge during the continual training stage and teach the model to lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15062","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/2305.15062/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":"2305.15062","created_at":"2026-07-05T07:00:44.746550+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.15062v2","created_at":"2026-07-05T07:00:44.746550+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15062","created_at":"2026-07-05T07:00:44.746550+00:00"},{"alias_kind":"pith_short_12","alias_value":"UBTLI5X2XY3X","created_at":"2026-07-05T07:00:44.746550+00:00"},{"alias_kind":"pith_short_16","alias_value":"UBTLI5X2XY3XSWG6","created_at":"2026-07-05T07:00:44.746550+00:00"},{"alias_kind":"pith_short_8","alias_value":"UBTLI5X2","created_at":"2026-07-05T07:00:44.746550+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24901","citing_title":"LLM Evolution as an Industry-Scale Ecosystem: A Lifecycle Perspective on Continual Learning","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11910","citing_title":"An Ontology-Guided Multi-Anchor Graph Retrieval Framework for Traffic Legal Liability Determination","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2406.11354","citing_title":"Preserving Knowledge in Large Language Model with Model-Agnostic Self-Decompression","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00106","citing_title":"LicenseGPT: A Fine-tuned Foundation Model for Publicly Available Dataset License Compliance","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2402.13116","citing_title":"A Survey on Knowledge Distillation of Large Language Models","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14554","citing_title":"VLegal-Bench: Cognitively Grounded Benchmark for Vietnamese Legal Reasoning of Large Language Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2601.21503","citing_title":"MAR: Efficient Large Language Models via Module-aware Architecture Refinement","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22764","citing_title":"Implicit Humanization in Everyday LLM Moral Judgments","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02472","citing_title":"Accurate Legal Reasoning at Scale: Neuro-Symbolic Offloading and Structural Auditability for Robust Legal Adjudication","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UBTLI5X2XY3XSWG6ZIIX7QLMM6","json":"https://pith.science/pith/UBTLI5X2XY3XSWG6ZIIX7QLMM6.json","graph_json":"https://pith.science/api/pith-number/UBTLI5X2XY3XSWG6ZIIX7QLMM6/graph.json","events_json":"https://pith.science/api/pith-number/UBTLI5X2XY3XSWG6ZIIX7QLMM6/events.json","paper":"https://pith.science/paper/UBTLI5X2"},"agent_actions":{"view_html":"https://pith.science/pith/UBTLI5X2XY3XSWG6ZIIX7QLMM6","download_json":"https://pith.science/pith/UBTLI5X2XY3XSWG6ZIIX7QLMM6.json","view_paper":"https://pith.science/paper/UBTLI5X2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.15062&json=true","fetch_graph":"https://pith.science/api/pith-number/UBTLI5X2XY3XSWG6ZIIX7QLMM6/graph.json","fetch_events":"https://pith.science/api/pith-number/UBTLI5X2XY3XSWG6ZIIX7QLMM6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UBTLI5X2XY3XSWG6ZIIX7QLMM6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UBTLI5X2XY3XSWG6ZIIX7QLMM6/action/storage_attestation","attest_author":"https://pith.science/pith/UBTLI5X2XY3XSWG6ZIIX7QLMM6/action/author_attestation","sign_citation":"https://pith.science/pith/UBTLI5X2XY3XSWG6ZIIX7QLMM6/action/citation_signature","submit_replication":"https://pith.science/pith/UBTLI5X2XY3XSWG6ZIIX7QLMM6/action/replication_record"}},"created_at":"2026-07-05T07:00:44.746550+00:00","updated_at":"2026-07-05T07:00:44.746550+00:00"}