{"id":"https://openalex.org/W4391092890","doi":"https://doi.org/10.1109/bigdata59044.2023.10386911","title":"Empirical Study of LLM Fine-Tuning for Text Classification in Legal Document Review","display_name":"Empirical Study of LLM Fine-Tuning for Text Classification in Legal Document Review","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4391092890","doi":"https://doi.org/10.1109/bigdata59044.2023.10386911"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata59044.2023.10386911","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata59044.2023.10386911","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052463733","display_name":"Fusheng Wei","orcid":"https://orcid.org/0009-0000-5881-5307"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fusheng Wei","raw_affiliation_strings":["Data & Technology Ankura Consulting Group, LLC,Washington, D.C,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data & Technology Ankura Consulting Group, LLC,Washington, D.C,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035561684","display_name":"Robert Keeling","orcid":null},"institutions":[{"id":"https://openalex.org/I861268105","display_name":"Sidley Austin","ror":"https://ror.org/05a8r2n20","country_code":"US","type":"other","lineage":["https://openalex.org/I861268105"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Keeling","raw_affiliation_strings":["Complex Commercial Litigation Sidley Austin LLP,Washington DC,USA","Complex Commercial Litigation Sidley Austin LLP, Washington DC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Complex Commercial Litigation Sidley Austin LLP,Washington DC,USA","institution_ids":["https://openalex.org/I861268105"]},{"raw_affiliation_string":"Complex Commercial Litigation Sidley Austin LLP, Washington DC, USA","institution_ids":["https://openalex.org/I861268105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049186333","display_name":"Nathaniel Huber-Fliflet","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nathaniel Huber-Fliflet","raw_affiliation_strings":["Data & Technology Ankura Consulting Group, LLC,Washington, D.C,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data & Technology Ankura Consulting Group, LLC,Washington, D.C,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390073","display_name":"Jianping Zhang","orcid":"https://orcid.org/0000-0002-4451-6661"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianping Zhang","raw_affiliation_strings":["Data & Technology Ankura Consulting Group, LLC,Washington, D.C,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data & Technology Ankura Consulting Group, LLC,Washington, D.C,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101619455","display_name":"Adam D\u0105browski","orcid":"https://orcid.org/0000-0002-9385-6080"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adam Dabrowski","raw_affiliation_strings":["Data & Technology Ankura Consulting Group, LLC,Washington, D.C,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data & Technology Ankura Consulting Group, LLC,Washington, D.C,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053350610","display_name":"Jingchao Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingchao Yang","raw_affiliation_strings":["Data & Technology Ankura Consulting Group, LLC,Washington, D.C,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data & Technology Ankura Consulting Group, LLC,Washington, D.C,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101453263","display_name":"Qiang Mao","orcid":"https://orcid.org/0000-0002-9382-6527"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiang Mao","raw_affiliation_strings":["Data & Technology Ankura Consulting Group, LLC,Washington, D.C,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data & Technology Ankura Consulting Group, LLC,Washington, D.C,USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101414673","display_name":"Han Qin","orcid":"https://orcid.org/0000-0001-9776-5007"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han Qin","raw_affiliation_strings":["Data & Technology Ankura Consulting Group, LLC,Washington, D.C,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data & Technology Ankura Consulting Group, LLC,Washington, D.C,USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":81.6618,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.99958757,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2786","last_page":"2792"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.9840999841690063,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.9840999841690063,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.925599992275238,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9162999987602234,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6412534713745117},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5030223727226257},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4544163644313812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41559404134750366}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6412534713745117},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5030223727226257},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4544163644313812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41559404134750366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata59044.2023.10386911","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata59044.2023.10386911","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.550000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2585689263","https://openalex.org/W2896457183","https://openalex.org/W2912267070","https://openalex.org/W2978017171","https://openalex.org/W2995674643","https://openalex.org/W3138482863","https://openalex.org/W4205757056","https://openalex.org/W4320024106","https://openalex.org/W4391092927","https://openalex.org/W6755207826","https://openalex.org/W6768851824"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0],"increased":[1],"integration":[2],"of":[3,29,55,75,93,100,130,133],"Large":[4,107],"Language":[5,108],"Models":[6],"(LLMs)":[7],"across":[8],"industry":[9],"sectors":[10],"is":[11],"enabling":[12],"domain":[13],"experts":[14],"with":[15],"new":[16],"text":[17,42,76,95,101,121,134],"classification":[18,102],"optimization":[19],"methods.":[20],"These":[21],"LLMs":[22],"are":[23],"pretrained":[24,60],"on":[25,152],"exceedingly":[26],"large":[27],"amounts":[28],"data;":[30],"however,":[31],"practitioners":[32],"can":[33],"perform":[34],"additional":[35],"training,":[36],"or":[37],"\u201cfine-tuning,\u201d":[38],"to":[39],"improve":[40],"their":[41,46],"classifier\u2019s":[43],"results":[44],"for":[45,70,122,135],"own":[47],"use":[48,154],"cases.":[49],"This":[50],"paper":[51],"presents":[52],"a":[53,58,64,118,131],"series":[54],"experiments":[56],"comparing":[57,138],"standard,":[59],"DistilBERT":[61,66],"model":[62,80],"and":[63,124],"fine-tuned":[65],"model,":[67],"both":[68],"leveraged":[69],"the":[71,79,91,98,139,149,153],"downstream":[72],"NLP":[73],"task":[74],"classification.":[77],"Tuning":[78],"using":[81,104],"domain-specific":[82],"data":[83],"from":[84],"real-world":[85],"legal":[86],"matters":[87],"suggests":[88],"fine-tuning":[89],"improves":[90],"performance":[92,99],"LLM":[94],"classifiers.To":[96],"evaluate":[97],"models,":[103],"these":[105],"two":[106,112,140],"Models,":[109],"we":[110,142],"employed":[111],"distinct":[113],"approaches":[114,141],"that":[115,144],"1)":[116],"score":[117,126],"whole":[119],"document\u2019s":[120],"prediction":[123,146],"2)":[125],"snippets":[127],"(sentence-level":[128],"components":[129],"document)":[132],"prediction.":[136],"When":[137],"found":[143],"one":[145],"method":[147],"outperforms":[148],"other,":[150],"depending":[151],"case.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":31},{"year":2024,"cited_by_count":9}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}