{"id":"https://openalex.org/W7123468188","doi":"https://doi.org/10.1145/3769126.3769227","title":"Automatic Legal Writing Evaluation of LLMs","display_name":"Automatic Legal Writing Evaluation of LLMs","publication_year":2025,"publication_date":"2025-06-16","ids":{"openalex":"https://openalex.org/W7123468188","doi":"https://doi.org/10.1145/3769126.3769227"},"language":null,"primary_location":{"id":"doi:10.1145/3769126.3769227","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769126.3769227","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twentieth International Conference on Artificial Intelligence and Law","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3769126.3769227","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086873271","display_name":"Ramon Pires","orcid":"https://orcid.org/0000-0002-0023-1971"},"institutions":[{"id":"https://openalex.org/I4210142333","display_name":"Centro de Tecnologia da Informa\u00e7\u00e3o Renato Archer","ror":"https://ror.org/044nfga98","country_code":"BR","type":"government","lineage":["https://openalex.org/I4210142333","https://openalex.org/I4210151455"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Ramon Pires","raw_affiliation_strings":["Maritaca AI, Campinas, S\u00e3o Paulo, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-0023-1971","affiliations":[{"raw_affiliation_string":"Maritaca AI, Campinas, S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I4210142333"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043424590","display_name":"Roseval Donisete Malaquias","orcid":"https://orcid.org/0000-0002-6005-0515"},"institutions":[{"id":"https://openalex.org/I4210142333","display_name":"Centro de Tecnologia da Informa\u00e7\u00e3o Renato Archer","ror":"https://ror.org/044nfga98","country_code":"BR","type":"government","lineage":["https://openalex.org/I4210142333","https://openalex.org/I4210151455"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Roseval Malaquias Junior","raw_affiliation_strings":["Maritaca AI, Campinas, S\u00e3o Paulo, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-6005-0515","affiliations":[{"raw_affiliation_string":"Maritaca AI, Campinas, S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I4210142333"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122945153","display_name":"Rodrigo Nogueira","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142333","display_name":"Centro de Tecnologia da Informa\u00e7\u00e3o Renato Archer","ror":"https://ror.org/044nfga98","country_code":"BR","type":"government","lineage":["https://openalex.org/I4210142333","https://openalex.org/I4210151455"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Rodrigo Nogueira","raw_affiliation_strings":["Maritaca AI, Campinas, S\u00e3o Paulo, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-2600-6035","affiliations":[{"raw_affiliation_string":"Maritaca AI, Campinas, S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I4210142333"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210142333"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"420","last_page":"424"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.3285999894142151,"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":0.3285999894142151,"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":0.1347000002861023,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.12520000338554382,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6554999947547913},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4595000147819519},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.4458000063896179},{"id":"https://openalex.org/keywords/frontier","display_name":"Frontier","score":0.35519999265670776},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.349700003862381}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6554999947547913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5198000073432922},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4595000147819519},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4458000063896179},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3492000102996826},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.32659998536109924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31940001249313354},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.2838999927043915},{"id":"https://openalex.org/C168725872","wikidata":"https://www.wikidata.org/wiki/Q991663","display_name":"Sophistication","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.26440000534057617},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2630999982357025},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3769126.3769227","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769126.3769227","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twentieth International Conference on Artificial Intelligence and Law","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3769126.3769227","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769126.3769227","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twentieth International Conference on Artificial Intelligence and Law","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5843687057495117,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W3099950029","https://openalex.org/W4366403195","https://openalex.org/W4385571232","https://openalex.org/W4385571576","https://openalex.org/W4389403907","https://openalex.org/W4389519254","https://openalex.org/W4389523927","https://openalex.org/W4401043863","https://openalex.org/W4402671800","https://openalex.org/W4404781000"],"related_works":[],"abstract_inverted_index":{"Despite":[0],"the":[1,17,29,77,98,110,169,181],"recent":[2,74],"advances":[3],"in":[4,24,32],"Large":[5],"Language":[6],"Models,":[7],"benchmarks":[8],"for":[9,137],"evaluating":[10,33,138,158],"legal":[11,139,174],"writing":[12,175],"remain":[13],"scarce":[14],"due":[15],"to":[16,92],"inherent":[18],"complexity":[19],"of":[20,28,71,76,100,117,120,173],"assessing":[21],"open-ended":[22],"responses":[23],"this":[25],"domain.":[26],"One":[27],"key":[30],"challenges":[31],"language":[34],"models":[35,146],"on":[36,103],"domain-specific":[37],"tasks":[38],"is":[39],"finding":[40,105],"test":[41],"datasets":[42],"that":[43,106,144],"are":[44,196],"public,":[45],"frequently":[46],"updated,":[47],"and":[48,85,180,190],"contain":[49],"comprehensive":[50,82],"evaluation":[51,83,186],"guidelines.":[52],"The":[53,79,177],"Brazilian":[54],"Bar":[55],"Examination":[56],"meets":[57],"these":[58],"requirements.":[59],"We":[60,96,126],"introduce":[61],"oab-bench,":[62,104],"a":[63,151],"benchmark":[64,80],"comprising":[65],"105":[66],"questions":[67],"across":[68],"seven":[69],"areas":[70],"law":[72],"from":[73],"editions":[75],"exam.":[78],"includes":[81],"guidelines":[84],"reference":[86],"materials":[87],"used":[88],"by":[89],"human":[90,155],"examiners":[91],"ensure":[93],"consistent":[94],"grading.":[95],"evaluate":[97],"performance":[99],"four":[101],"LLMs":[102,130],"Claude-3.5":[107],"Sonnet":[108],"achieves":[109],"best":[111],"results":[112],"with":[113,154],"an":[114],"average":[115],"score":[116],"7.93":[118],"out":[119],"10,":[121],"passing":[122],"all":[123],"21":[124],"exams.":[125],"also":[127],"investigated":[128],"whether":[129],"can":[131],"serve":[132],"as":[133,164],"reliable":[134,165],"automated":[135,166,193],"judges":[136],"writing.":[140],"Our":[141],"experiments":[142],"show":[143],"frontier":[145],"like":[147],"OpenAI\u2019s":[148],"o1":[149],"achieve":[150],"strong":[152],"correlation":[153],"scores":[156],"when":[157],"approved":[159],"exams,":[160],"suggesting":[161],"their":[162,191],"potential":[163],"evaluators":[167],"despite":[168],"inherently":[170],"subjective":[171],"nature":[172],"assessment.":[176],"source":[178],"code1":[179],"benchmark2":[182],"\u2013":[183,195],"containing":[184],"questions,":[185],"guidelines,":[187],"model-generated":[188],"responses,":[189],"respective":[192],"evaluations":[194],"publicly":[197],"available.":[198]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-14T00:00:00"}
