{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R46Y6JGDFOPLGY5GFXCVOZ4ZBI","short_pith_number":"pith:R46Y6JGD","schema_version":"1.0","canonical_sha256":"8f3d8f24c32b9eb363a62dc55767990a083b6246b46d57cbe36d08d9fbd2992f","source":{"kind":"arxiv","id":"2401.02981","version":2},"attestation_state":"computed","paper":{"title":"Fine-tuning and Utilization Methods of Domain-specific LLMs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cheonsu Jeong","submitted_at":"2024-01-01T06:22:04Z","abstract_excerpt":"Recent releases of pre-trained Large Language Models (LLMs) have gained considerable traction, yet research on fine-tuning and employing domain-specific LLMs remains scarce. This study investigates approaches for fine-tuning and leveraging domain-specific LLMs, highlighting trends in LLMs, foundational models, and methods for domain-specific pre-training. Focusing on the financial sector, it details dataset selection, preprocessing, model choice, and considerations crucial for LLM fine-tuning in finance. Addressing the unique characteristics of financial data, the study explores the constructi"},"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":"2401.02981","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-01T06:22:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3a14cac763570619f6c3b5c83203c31ebd7c6742ea123a5e26659d3d6eee9f0e","abstract_canon_sha256":"cac58ad05f12cd4992eef57234537d8b5dfc6e3c719a25adc5b979009fd24d6a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:59.515759Z","signature_b64":"4/YLHMJsYCFKvRES+MkCjD8vF6pBWRRpbHKlpObp/Rk+u7q6PeVMOA8hj+cZFyWDq/z25yBCovCgj7eOw44LBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f3d8f24c32b9eb363a62dc55767990a083b6246b46d57cbe36d08d9fbd2992f","last_reissued_at":"2026-07-05T08:23:59.515298Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:59.515298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-tuning and Utilization Methods of Domain-specific LLMs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cheonsu Jeong","submitted_at":"2024-01-01T06:22:04Z","abstract_excerpt":"Recent releases of pre-trained Large Language Models (LLMs) have gained considerable traction, yet research on fine-tuning and employing domain-specific LLMs remains scarce. This study investigates approaches for fine-tuning and leveraging domain-specific LLMs, highlighting trends in LLMs, foundational models, and methods for domain-specific pre-training. Focusing on the financial sector, it details dataset selection, preprocessing, model choice, and considerations crucial for LLM fine-tuning in finance. Addressing the unique characteristics of financial data, the study explores the constructi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02981","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/2401.02981/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":"2401.02981","created_at":"2026-07-05T08:23:59.515362+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.02981v2","created_at":"2026-07-05T08:23:59.515362+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02981","created_at":"2026-07-05T08:23:59.515362+00:00"},{"alias_kind":"pith_short_12","alias_value":"R46Y6JGDFOPL","created_at":"2026-07-05T08:23:59.515362+00:00"},{"alias_kind":"pith_short_16","alias_value":"R46Y6JGDFOPLGY5G","created_at":"2026-07-05T08:23:59.515362+00:00"},{"alias_kind":"pith_short_8","alias_value":"R46Y6JGD","created_at":"2026-07-05T08:23:59.515362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04572","citing_title":"From Parameter Dynamics to Risk Scoring : Quantifying Sample-Level Safety Degradation in LLM Fine-tuning","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R46Y6JGDFOPLGY5GFXCVOZ4ZBI","json":"https://pith.science/pith/R46Y6JGDFOPLGY5GFXCVOZ4ZBI.json","graph_json":"https://pith.science/api/pith-number/R46Y6JGDFOPLGY5GFXCVOZ4ZBI/graph.json","events_json":"https://pith.science/api/pith-number/R46Y6JGDFOPLGY5GFXCVOZ4ZBI/events.json","paper":"https://pith.science/paper/R46Y6JGD"},"agent_actions":{"view_html":"https://pith.science/pith/R46Y6JGDFOPLGY5GFXCVOZ4ZBI","download_json":"https://pith.science/pith/R46Y6JGDFOPLGY5GFXCVOZ4ZBI.json","view_paper":"https://pith.science/paper/R46Y6JGD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.02981&json=true","fetch_graph":"https://pith.science/api/pith-number/R46Y6JGDFOPLGY5GFXCVOZ4ZBI/graph.json","fetch_events":"https://pith.science/api/pith-number/R46Y6JGDFOPLGY5GFXCVOZ4ZBI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R46Y6JGDFOPLGY5GFXCVOZ4ZBI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R46Y6JGDFOPLGY5GFXCVOZ4ZBI/action/storage_attestation","attest_author":"https://pith.science/pith/R46Y6JGDFOPLGY5GFXCVOZ4ZBI/action/author_attestation","sign_citation":"https://pith.science/pith/R46Y6JGDFOPLGY5GFXCVOZ4ZBI/action/citation_signature","submit_replication":"https://pith.science/pith/R46Y6JGDFOPLGY5GFXCVOZ4ZBI/action/replication_record"}},"created_at":"2026-07-05T08:23:59.515362+00:00","updated_at":"2026-07-05T08:23:59.515362+00:00"}