{"id":"https://openalex.org/W4413267863","doi":"https://doi.org/10.1145/3696630.3728530","title":"LicenseGPT: A Fine-tuned Foundation Model for Publicly Available Dataset License Compliance","display_name":"LicenseGPT: A Fine-tuned Foundation Model for Publicly Available Dataset License Compliance","publication_year":2025,"publication_date":"2025-06-23","ids":{"openalex":"https://openalex.org/W4413267863","doi":"https://doi.org/10.1145/3696630.3728530"},"language":"en","primary_location":{"id":"doi:10.1145/3696630.3728530","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696630.3728530","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 33rd ACM International Conference on the Foundations of Software Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3696630.3728530","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102319187","display_name":"Jun Tan","orcid":"https://orcid.org/0009-0004-8249-8363"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jingwen Tan","raw_affiliation_strings":["School of Software Engineering, Sun Yat-Sen University, zhuhai, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Sun Yat-Sen University, zhuhai, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052055475","display_name":"Gopi Krishnan Rajbahadur","orcid":"https://orcid.org/0000-0003-1812-5365"},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Gopi Krishnan Rajbahadur","raw_affiliation_strings":["Centre for Software Excellence, Huawei, Canada, Ottawa, Canada"],"affiliations":[{"raw_affiliation_string":"Centre for Software Excellence, Huawei, Canada, Ottawa, Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021665372","display_name":"Zi Qiang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zi Li","raw_affiliation_strings":["Huawei China, shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei China, shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112268472","display_name":"Xiangfu Song","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xiangfu Song","raw_affiliation_strings":["Centre for Software Excellence, Huawei, Canada, Ottawa, Canada"],"affiliations":[{"raw_affiliation_string":"Centre for Software Excellence, Huawei, Canada, Ottawa, Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112136256","display_name":"Jaw-Guei Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA","CN"],"is_corresponding":false,"raw_author_name":"Jianshan Lin","raw_affiliation_strings":["Huawei China, shenzhen, Canada"],"affiliations":[{"raw_affiliation_string":"Huawei China, shenzhen, Canada","institution_ids":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100380723","display_name":"Dan Li","orcid":"https://orcid.org/0000-0002-3787-1673"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Li","raw_affiliation_strings":["School of Software Engineering, Sun Yat-Sen University, zhuhai, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Sun Yat-Sen University, zhuhai, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000582109","display_name":"Zibin Zheng","orcid":"https://orcid.org/0000-0002-7878-4330"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zibin Zheng","raw_affiliation_strings":["School of Software Engineering, Sun Yat-Sen University, zhuhai, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Sun Yat-Sen University, zhuhai, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091586373","display_name":"Ahmed E. Hassan","orcid":"https://orcid.org/0000-0001-7749-5513"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ahmed E. Hassan","raw_affiliation_strings":["Queen's University, Kingston, Canada"],"affiliations":[{"raw_affiliation_string":"Queen's University, Kingston, Canada","institution_ids":["https://openalex.org/I204722609"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5102319187"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":4.4085,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.95324059,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"50"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9649999737739563,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9621999859809875,"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/foundation","display_name":"Foundation (evidence)","score":0.8031697273254395},{"id":"https://openalex.org/keywords/license","display_name":"License","score":0.7341945171356201},{"id":"https://openalex.org/keywords/compliance","display_name":"Compliance (psychology)","score":0.6153391003608704},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.583838164806366},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.36364468932151794},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.0571821928024292}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.8031697273254395},{"id":"https://openalex.org/C2780560020","wikidata":"https://www.wikidata.org/wiki/Q79719","display_name":"License","level":2,"score":0.7341945171356201},{"id":"https://openalex.org/C2781460075","wikidata":"https://www.wikidata.org/wiki/Q1399332","display_name":"Compliance (psychology)","level":2,"score":0.6153391003608704},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.583838164806366},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.36364468932151794},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0571821928024292},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3696630.3728530","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696630.3728530","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 33rd ACM International Conference on the Foundations of Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3696630.3728530","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696630.3728530","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 33rd ACM International Conference on the Foundations of Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2007023841","https://openalex.org/W2030573703","https://openalex.org/W2038625040","https://openalex.org/W2061554433","https://openalex.org/W2079039933","https://openalex.org/W2107930672","https://openalex.org/W2126843316","https://openalex.org/W2147209048","https://openalex.org/W2148766740","https://openalex.org/W2469415976","https://openalex.org/W2787485658","https://openalex.org/W2911599914","https://openalex.org/W2922234936","https://openalex.org/W2935234963","https://openalex.org/W2939930770","https://openalex.org/W2963520355","https://openalex.org/W2974071289","https://openalex.org/W3126989030","https://openalex.org/W3181307617","https://openalex.org/W3190472000","https://openalex.org/W3208577398","https://openalex.org/W3212368439","https://openalex.org/W4221159410","https://openalex.org/W4300870773","https://openalex.org/W4322718191","https://openalex.org/W4366327277","https://openalex.org/W4378508560","https://openalex.org/W4379466620","https://openalex.org/W4382618722","https://openalex.org/W4385570658","https://openalex.org/W4386114274","https://openalex.org/W4391611012","https://openalex.org/W4392358084","https://openalex.org/W4394906077","https://openalex.org/W4396775772","https://openalex.org/W6664269781","https://openalex.org/W6778883912","https://openalex.org/W6785559428","https://openalex.org/W6846002521","https://openalex.org/W6851775633","https://openalex.org/W6853444283","https://openalex.org/W6908510789","https://openalex.org/W7046559209"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2606446052","https://openalex.org/W2036021480","https://openalex.org/W3195777957","https://openalex.org/W2382668227","https://openalex.org/W2348482143","https://openalex.org/W2024584030","https://openalex.org/W3104168426"],"abstract_inverted_index":{"Dataset":[0],"license":[1,60,205],"compliance":[2,61],"is":[3],"a":[4,51,85,95,153,184],"critical":[5],"yet":[6],"complex":[7,168],"aspect":[8],"of":[9,19,89,98,175],"developing":[10],"commercial":[11],"AI":[12,177,199,219],"products,":[13],"particularly":[14],"with":[15,123],"the":[16,81,162,173,195],"increasing":[17],"use":[18],"publicly":[20,185],"available":[21,186],"datasets.":[22],"Ambiguities":[23],"in":[24,72,167,179,202],"dataset":[25,59,97],"licenses":[26,100],"pose":[27],"significant":[28],"legal":[29,67,76,103,112,180,209],"risks,":[30],"making":[31],"it":[32],"challenging":[33],"even":[34],"for":[35,58,164,188],"software":[36,124,200,220],"IP":[37,125,148],"lawyers":[38,149],"to":[39,108,139,197,212],"accurately":[40],"interpret":[41],"rights":[42],"and":[43,74,78,113,120,182,190,217],"obligations.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,127],"introduce":[49],"LicenseGPT,":[50,92],"fine-tuned":[52,93],"foundation":[53],"model":[54,83],"(FM)":[55],"specifically":[56],"designed":[57],"analysis.":[62],"We":[63],"first":[64],"evaluate":[65],"existing":[66],"FMs":[68,70],"(i.e.,":[69],"specialized":[71,176],"understanding":[73],"processing":[75],"texts)":[77],"find":[79],"that":[80,129,157],"best-performing":[82],"achieves":[84],"Prediction":[86],"Agreement":[87],"(PA)":[88],"only":[90],"43.75%.":[91],"on":[94],"curated":[96],"500":[99],"annotated":[101],"by":[102,134],"experts,":[104],"significantly":[105],"improves":[106],"PA":[107],"64.30%,":[109],"outperforming":[110],"both":[111],"general-purpose":[114],"FMs.":[115],"Through":[116],"an":[117],"A/B":[118],"test":[119],"user":[121],"study":[122],"lawyers,":[126],"demonstrate":[128],"LicenseGPT":[130,151,193],"reduces":[131],"analysis":[132],"time":[133],"94.44%,":[135],"from":[136],"108":[137],"seconds":[138,141],"6":[140],"per":[142],"license,":[143],"without":[144],"compromising":[145],"accuracy.":[146],"Software":[147],"perceive":[150],"as":[152],"valuable":[154],"supplementary":[155],"tool":[156],"enhances":[158],"efficiency":[159],"while":[160],"acknowledging":[161],"need":[163],"human":[165],"oversight":[166],"cases.":[169],"Our":[170],"work":[171],"underscores":[172],"potential":[174,196],"tools":[178],"practice":[181],"offers":[183],"resource":[187],"practitioners":[189],"researchers.":[191],"Moreover,":[192],"has":[194],"assist":[198],"developers":[201],"managing":[203],"preliminary":[204],"checks":[206],"before":[207],"involving":[208],"counsel,":[210],"helping":[211],"avoid":[213],"costly":[214],"late-stage":[215],"rework":[216],"ensuring":[218],"compliance.":[221]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}