{"id":"https://openalex.org/W4408564325","doi":"https://doi.org/10.1016/j.mlwa.2025.100639","title":"Software engineering meets legal texts: LLMs for auto detection of contract smells","display_name":"Software engineering meets legal texts: LLMs for auto detection of contract smells","publication_year":2025,"publication_date":"2025-03-18","ids":{"openalex":"https://openalex.org/W4408564325","doi":"https://doi.org/10.1016/j.mlwa.2025.100639"},"language":"en","primary_location":{"id":"doi:10.1016/j.mlwa.2025.100639","doi":"https://doi.org/10.1016/j.mlwa.2025.100639","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.mlwa.2025.100639","pdf_url":null,"source":{"id":"https://openalex.org/S4210201048","display_name":"Machine Learning with Applications","issn_l":"2666-8270","issn":["2666-8270"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-d","jufo-1","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning with Applications","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1016/j.mlwa.2025.100639","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119863995","display_name":"Moriya Dechtiar","orcid":"https://orcid.org/0009-0007-6414-7553","observed_orcids":["https://orcid.org/0009-0007-6414-7553"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Moriya Dechtiar","raw_affiliation_strings":["Harvard University, Cambridge, 02138, MA, USA"],"raw_orcid":"https://orcid.org/0009-0007-6414-7553","affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, 02138, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038615036","display_name":"Daniel Martin Katz","orcid":"https://orcid.org/0000-0002-9775-0320","observed_orcids":["https://orcid.org/0000-0002-9775-0320","https://orcid.org/0000-0003-2720-0339"]},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]},{"id":"https://openalex.org/I205023500","display_name":"Chicago Kent College of Law","ror":"https://ror.org/0062tv278","country_code":"US","type":"education","lineage":["https://openalex.org/I205023500"]},{"id":"https://openalex.org/I90523175","display_name":"Bucerius Law School","ror":"https://ror.org/05c11k793","country_code":"DE","type":"education","lineage":["https://openalex.org/I90523175"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Daniel Martin Katz","raw_affiliation_strings":["Center for Legal Technology & Data Science, Bucerius Law School, Hamburg, 20355, Germany","CodeX - The Stanford Center for Legal Informatics, Stanford, 94305, CA, USA","Illinois Tech-Chicago Kent College of Law, Chicago, 60616, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Legal Technology & Data Science, Bucerius Law School, Hamburg, 20355, Germany","institution_ids":["https://openalex.org/I90523175"]},{"raw_affiliation_string":"CodeX - The Stanford Center for Legal Informatics, Stanford, 94305, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Illinois Tech-Chicago Kent College of Law, Chicago, 60616, IL, USA","institution_ids":["https://openalex.org/I180949307","https://openalex.org/I205023500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101675012","display_name":"Hongming Wang","orcid":"https://orcid.org/0009-0003-3507-4261","observed_orcids":["https://orcid.org/0009-0003-3507-4261"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongming Wang","raw_affiliation_strings":["Harvard University, Cambridge, 02138, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, 02138, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5119863995"],"corresponding_institution_ids":["https://openalex.org/I136199984"],"apc_list":{"value":2340,"currency":"USD","value_usd":2340},"apc_paid":{"value":2340,"currency":"USD","value_usd":2340},"fwci":7.7,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.95809074,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"20","issue":null,"first_page":"100639","last_page":"100639"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.9961000084877014,"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":0.9961000084877014,"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":0.0027000000700354576,"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/T10260","display_name":"Software Engineering Research","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/code-smells","display_name":"code smells","score":0.5669999718666077},{"id":"https://openalex.org/keywords/contract-drafting","display_name":"contract drafting","score":0.5460000038146973},{"id":"https://openalex.org/keywords/automated-anomaly-detection","display_name":"automated anomaly detection","score":0.7200000286102295},{"id":"https://openalex.org/keywords/legal-bert","display_name":"Legal-BERT","score":0.7950000166893005},{"id":"https://openalex.org/keywords/bert-fine-tuning","display_name":"BERT fine-tuning","score":0.9559999704360962}],"concepts":[{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5093525648117065},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4752652049064636},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4528277516365051},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.40944331884384155},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.3724871873855591},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19411435723304749}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.mlwa.2025.100639","doi":"https://doi.org/10.1016/j.mlwa.2025.100639","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.mlwa.2025.100639","pdf_url":null,"source":{"id":"https://openalex.org/S4210201048","display_name":"Machine Learning with Applications","issn_l":"2666-8270","issn":["2666-8270"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-d","jufo-1","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning with Applications","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:28bfff7ae02444ce8587fffb155952d1","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/28bfff7ae02444ce8587fffb155952d1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning with Applications, Vol 20, Iss , Pp 100639- (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1016/j.mlwa.2025.100639","doi":"https://doi.org/10.1016/j.mlwa.2025.100639","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.mlwa.2025.100639","pdf_url":null,"source":{"id":"https://openalex.org/S4210201048","display_name":"Machine Learning with Applications","issn_l":"2666-8270","issn":["2666-8270"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-d","jufo-1","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning with Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W121426601","https://openalex.org/W649920412","https://openalex.org/W2097999976","https://openalex.org/W2153887189","https://openalex.org/W2159809641","https://openalex.org/W2166492919","https://openalex.org/W2750779823","https://openalex.org/W2765810309","https://openalex.org/W2787379525","https://openalex.org/W2796404405","https://openalex.org/W2805389643","https://openalex.org/W2919470919","https://openalex.org/W2963341956","https://openalex.org/W2995996336","https://openalex.org/W3005595604","https://openalex.org/W3035668167","https://openalex.org/W3092129462","https://openalex.org/W3092221863","https://openalex.org/W3101118213","https://openalex.org/W3121904249","https://openalex.org/W3132426458","https://openalex.org/W3134714752","https://openalex.org/W3190979059","https://openalex.org/W3199367723","https://openalex.org/W3201977280","https://openalex.org/W3204112174","https://openalex.org/W4214835948","https://openalex.org/W4234335579","https://openalex.org/W4240648738","https://openalex.org/W4244034183","https://openalex.org/W4247737564","https://openalex.org/W4248491408","https://openalex.org/W4281635622","https://openalex.org/W4318586794","https://openalex.org/W4381855801","https://openalex.org/W4388483889","https://openalex.org/W4389403907","https://openalex.org/W4389519153","https://openalex.org/W4389519438","https://openalex.org/W4391093139","https://openalex.org/W4392477373","https://openalex.org/W4400992318","https://openalex.org/W4404792899","https://openalex.org/W4405432856","https://openalex.org/W4406458261","https://openalex.org/W6851024552"],"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/W4396696052"],"abstract_inverted_index":{"Although":[0],"there":[1],"have":[2],"been":[3],"many":[4],"major":[5],"advances":[6],"in":[7],"Artificial":[8],"Intelligence":[9],"including":[10],"its":[11],"application":[12],"to":[13,24,46,77,175],"a":[14,183],"wide":[15],"variety":[16],"of":[17,59,83,86,97,118,143,160,168,178,196,206,229],"tasks,":[18],"some":[19],"specialized":[20],"domains":[21],"remain":[22],"difficult":[23],"tackle.":[25],"In":[26],"this":[27,152,163],"work,":[28],"we":[29,50,93],"examine":[30],"parallels":[31],"between":[32],"software":[33,197],"engineering":[34,198],"and":[35,39,73,104,173,191,209,222,231],"legal":[36,48,98,179,189],"contract":[37,88,161,180,201],"drafting":[38,190],"analysis.":[40,192],"Porting":[41],"well-known":[42],"code":[43],"smells":[44],"principles":[45,199],"various":[47],"contracts,":[49],"introduce":[51],"\u201dcontract":[52,207],"smells,\u201d":[53],"text":[54],"patterns":[55],"that":[56,136],"are":[57],"indicative":[58],"potentially":[60],"significant":[61],"issues":[62],"within":[63],"contractual":[64],"agreements.":[65],"We":[66,111,133],"leverage":[67],"semi-auto":[68],"labeling":[69,218],"with":[70,115,219],"GPT-4,":[71],"prompting":[72],"expert":[74,223],"spot":[75],"checks,":[76],"create":[78],"datasets":[79],"for":[80],"suitability":[81],"testing":[82],"auto":[84],"detection":[85,109,139,147],"these":[87],"smells.":[89],"Using":[90],"transformer-based":[91],"models,":[92],"explore":[94],"the":[95,158,166],"impact":[96],"domain":[99],"knowledge,":[100],"hyperparameters":[101],"fine":[102],"tuning":[103],"specific":[105],"task":[106],"information":[107],"on":[108,242],"success.":[110],"achieve":[112],"high":[113],"accuracy":[114],"further":[116,134],"fine-tuning":[117],"BERT":[119],"as":[120,122],"well":[121],"LEGAL-BERT,":[123],"while":[124],"more":[125],"consistent":[126],"results":[127,228],"were":[128],"achieved":[129],"using":[130],"task-specific":[131,232],"data.":[132],"demonstrate":[135],"although":[137],"multi-class":[138],"can":[140],"boost":[141],"coverage":[142],"rare":[144],"smells,":[145,162],"single-class":[146,240],"yields":[148],"better":[149],"accuracy.":[150],"While":[151],"is":[153],"an":[154],"initial":[155],"foray":[156],"into":[157,200],"idea":[159],"work":[164],"underscores":[165],"feasibility":[167],"applying":[169],"advanced":[170],"NLP":[171],"techniques":[172],"LLMs":[174],"automate":[176],"aspects":[177],"review,":[181],"suggesting":[182],"scalable":[184,216],"path":[185],"toward":[186],"standardized,":[187],"machine-assisted":[188],"\u2022":[193,203,214,225,234],"Showcased":[194],"introduction":[195],"drafting.":[202],"Pioneered":[204],"concepts":[205],"smells\u201d":[208],"their":[210],"automated":[211],"anomaly":[212],"detection.":[213],"Demonstrated":[215],"semi-automated":[217],"GPT":[220],"prompts":[221],"validation.":[224],"Successful":[226],"auto-detection":[227],"pre-trained":[230],"LLMs.":[233],"Multi-class":[235],"models":[236],"aid":[237],"complex":[238],"smells;":[239],"outperforms":[241],"common":[243],"ones.":[244]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}