{"id":"https://openalex.org/W4392619035","doi":"https://doi.org/10.48550/arxiv.2403.03883","title":"SaulLM-7B: A pioneering Large Language Model for Law","display_name":"SaulLM-7B: A pioneering Large Language Model for Law","publication_year":2024,"publication_date":"2024-03-06","ids":{"openalex":"https://openalex.org/W4392619035","doi":"https://doi.org/10.48550/arxiv.2403.03883"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2403.03883","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.03883","pdf_url":"https://arxiv.org/pdf/2403.03883","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.03883","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078517761","display_name":"Pierre Colombo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210107720","display_name":"CentraleSup\u00e9lec","ror":"https://ror.org/019tcpt25","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I4210107720"]},{"id":"https://openalex.org/I4387152683","display_name":"Math\u00e9matiques et Informatique pour la Complexit\u00e9 et les Syst\u00e8mes","ror":"https://ror.org/03q29s414","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4387152683"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Colombo, Pierre","raw_affiliation_strings":["Equall.ai , New York , Paris , Lisbon","MICS , CentraleSup\u00e9lec , Universit\u00e9 Paris-Saclay","MICS - Math\u00e9matiques et Informatique pour la Complexit\u00e9 et les Syst\u00e8mes (Plateau de Moulon 3 rue Joliot Curie 91192 GIF SUR YVETTE CEDEX - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Equall.ai , New York , Paris , Lisbon","institution_ids":[]},{"raw_affiliation_string":"MICS , CentraleSup\u00e9lec , Universit\u00e9 Paris-Saclay","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I4210107720"]},{"raw_affiliation_string":"MICS - Math\u00e9matiques et Informatique pour la Complexit\u00e9 et les Syst\u00e8mes (Plateau de Moulon 3 rue Joliot Curie 91192 GIF SUR YVETTE CEDEX - France)","institution_ids":["https://openalex.org/I4387152683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112838866","display_name":"Telmo Pires","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pires, Telmo Pessoa","raw_affiliation_strings":["Equall.ai , New York , Paris , Lisbon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Equall.ai , New York , Paris , Lisbon","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008594421","display_name":"Malik Boudiaf","orcid":"https://orcid.org/0000-0003-2047-6447","observed_orcids":["https://orcid.org/0000-0003-2047-6447"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boudiaf, Malik","raw_affiliation_strings":["Equall.ai , New York , Paris , Lisbon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Equall.ai , New York , Paris , Lisbon","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Culver, Dominic","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Culver, Dominic","raw_affiliation_strings":["Equall.ai , New York , Paris , Lisbon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Equall.ai , New York , Paris , Lisbon","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101696636","display_name":"Rui Melo","orcid":"https://orcid.org/0009-0007-0009-0463","observed_orcids":["https://orcid.org/0009-0007-0009-0463"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Melo, Rui","raw_affiliation_strings":["Equall.ai , New York , Paris , Lisbon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Equall.ai , New York , Paris , Lisbon","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045551176","display_name":"Caio Corro","orcid":"https://orcid.org/0000-0001-7443-4109","observed_orcids":["https://orcid.org/0000-0001-7443-4109"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210150358","display_name":"Institut Syst\u00e8mes Intelligents et de Robotique","ror":"https://ror.org/05neq8668","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Corro, Caio","raw_affiliation_strings":["Sorbonne Universit\u00e9 , CNRS , ISIR , Paris"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9 , CNRS , ISIR , Paris","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210150358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051693368","display_name":"Andr\u00e9 F. T. Martins","orcid":"https://orcid.org/0000-0001-8282-625X","observed_orcids":["https://orcid.org/0000-0001-8282-625X","https://orcid.org/0000-0001-6863-4681"]},"institutions":[{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]},{"id":"https://openalex.org/I4387152517","display_name":"Instituto Superior T\u00e9cnico","ror":"https://ror.org/03db2by73","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103","https://openalex.org/I4387152517"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Martins, Andre F. T.","raw_affiliation_strings":["Instituto Superior T\u00e9cnico , Universidade de Lisboa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto Superior T\u00e9cnico , Universidade de Lisboa","institution_ids":["https://openalex.org/I141596103","https://openalex.org/I4387152517"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Esposito, Fabrizio","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I83558840","display_name":"Universidade Nova de Lisboa","ror":"https://ror.org/02xankh89","country_code":"PT","type":"education","lineage":["https://openalex.org/I83558840"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Esposito, Fabrizio","raw_affiliation_strings":["NOVA School of Law , Lisboa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NOVA School of Law , Lisboa","institution_ids":["https://openalex.org/I83558840"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087483601","display_name":"Vera L\u00facia Raposo","orcid":"https://orcid.org/0000-0001-7895-2181","observed_orcids":["https://orcid.org/0000-0001-7895-2181"]},"institutions":[{"id":"https://openalex.org/I83558840","display_name":"Universidade Nova de Lisboa","ror":"https://ror.org/02xankh89","country_code":"PT","type":"education","lineage":["https://openalex.org/I83558840"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Raposo, Vera L\u00facia","raw_affiliation_strings":["NOVA School of Law , Lisboa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NOVA School of Law , Lisboa","institution_ids":["https://openalex.org/I83558840"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Morgado, Sofia","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Morgado, Sofia","raw_affiliation_strings":["Equall.ai , New York , Paris , Lisbon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Equall.ai , New York , Paris , Lisbon","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049956936","display_name":"Michael Desa","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Desa, Michael","raw_affiliation_strings":["Equall.ai , New York , Paris , Lisbon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Equall.ai , New York , Paris , Lisbon","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.885699987411499,"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":0.885699987411499,"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":0.1080000028014183,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0019000000320374966,"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/legal-text-comprehension","display_name":"legal text comprehension","score":0.9369999766349792},{"id":"https://openalex.org/keywords/legal-text-generation","display_name":"legal text generation","score":0.8309999704360962},{"id":"https://openalex.org/keywords/legal-document-processing","display_name":"legal document processing","score":0.6119999885559082},{"id":"https://openalex.org/keywords/mistral-7b","display_name":"Mistral-7B","score":0.847000002861023},{"id":"https://openalex.org/keywords/legal-datasets","display_name":"legal datasets","score":0.6800000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7147266268730164},{"id":"https://openalex.org/C2780560020","wikidata":"https://www.wikidata.org/wiki/Q79719","display_name":"License","level":2,"score":0.5976572036743164},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.5786476731300354},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.5488989949226379},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5364165306091309},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5352950692176819},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46802717447280884},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4214913845062256},{"id":"https://openalex.org/C2776502561","wikidata":"https://www.wikidata.org/wiki/Q1713997","display_name":"Legal writing","level":3,"score":0.41422438621520996},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3974297046661377},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37124326825141907},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3218751549720764},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.30456823110580444},{"id":"https://openalex.org/C522695570","wikidata":"https://www.wikidata.org/wiki/Q6517578","display_name":"Legal research","level":2,"score":0.29363054037094116},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2696413993835449},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.1589617133140564},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.07523822784423828},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.06419932842254639},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2403.03883","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.03883","pdf_url":"https://arxiv.org/pdf/2403.03883","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-04574874v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-04574874","pdf_url":"https://hal.science/hal-04574874v1/file/2403.03883v2.pdf","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2024","raw_type":"info:eu-repo/semantics/preprint"},{"id":"doi:10.48550/arxiv.2403.03883","doi":"https://doi.org/10.48550/arxiv.2403.03883","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.03883","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.03883","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.03883","pdf_url":"https://arxiv.org/pdf/2403.03883","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6207000017166138,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions"}],"sustainable_development_goals_aurora":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320326256","display_name":"Grand \u00c9quipement National De Calcul Intensif","ror":"https://ror.org/0010d1q40"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392619035.pdf","grobid_xml":"https://content.openalex.org/works/W4392619035.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7152512440","https://openalex.org/W4416036154","https://openalex.org/W4415800806","https://openalex.org/W4414593777","https://openalex.org/W4417523023","https://openalex.org/W4399990902","https://openalex.org/W7125400440","https://openalex.org/W4386942328","https://openalex.org/W7038147883","https://openalex.org/W4417166488"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,65],"introduce":[4],"SaulLM-7B,":[5],"a":[6,67],"large":[7],"language":[8],"model":[9],"(LLM)":[10],"tailored":[11],"for":[12,27],"the":[13,22,34,88],"legal":[14,28,47,62,74,82],"domain.":[15],"With":[16],"7":[17],"billion":[18,52],"parameters,":[19],"SaulLM-7B":[20,41,54,84],"is":[21,42,85],"first":[23],"LLM":[24],"designed":[25],"explicitly":[26],"text":[29],"comprehension":[30],"and":[31,60],"generation.":[32],"Leveraging":[33],"Mistral":[35],"7B":[36],"architecture":[37],"as":[38],"its":[39],"foundation,":[40],"trained":[43],"on":[44],"an":[45],"English":[46],"corpus":[48],"of":[49],"over":[50],"30":[51],"tokens.":[53],"exhibits":[55],"state-of-the-art":[56],"proficiency":[57],"in":[58,81],"understanding":[59],"processing":[61],"documents.":[63],"Additionally,":[64],"present":[66],"novel":[68],"instructional":[69],"fine-tuning":[70],"method":[71],"that":[72],"leverages":[73],"datasets":[75],"to":[76],"further":[77],"enhance":[78],"SaulLM-7B's":[79],"performance":[80],"tasks.":[83],"released":[86],"under":[87],"MIT":[89],"License.":[90]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6}],"updated_date":"2026-10-27T15:51:10.671819","created_date":"2024-03-10T00:00:00"}
