{"id":"https://openalex.org/W4416988617","doi":"https://doi.org/10.3233/faia251579","title":"A Two-Dimensional Evaluation Framework for Factual and Reasoning Assessment of LLMs in Legal Question Answering","display_name":"A Two-Dimensional Evaluation Framework for Factual and Reasoning Assessment of LLMs in Legal Question Answering","publication_year":2025,"publication_date":"2025-12-02","ids":{"openalex":"https://openalex.org/W4416988617","doi":"https://doi.org/10.3233/faia251579"},"language":"en","primary_location":{"id":"doi:10.3233/faia251579","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251579","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia251579","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120633727","display_name":"Sinan Gultekin","orcid":null},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Sinan Gultekin","raw_affiliation_strings":["CIRSFID Alma-AI, Faculty of Law, University of Bologna, Italy"],"affiliations":[{"raw_affiliation_string":"CIRSFID Alma-AI, Faculty of Law, University of Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120633728","display_name":"Matteo Rossi Reich","orcid":null},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Matteo Rossi Reich","raw_affiliation_strings":["CIRSFID Alma-AI, Faculty of Law, University of Bologna, Italy"],"affiliations":[{"raw_affiliation_string":"CIRSFID Alma-AI, Faculty of Law, University of Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120684365","display_name":"Francesca Galloni","orcid":null},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesca Galloni","raw_affiliation_strings":["CIRSFID Alma-AI, Faculty of Law, University of Bologna, Italy"],"affiliations":[{"raw_affiliation_string":"CIRSFID Alma-AI, Faculty of Law, University of Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078176771","display_name":"Francesca Lagioia","orcid":"https://orcid.org/0000-0001-7083-3487"},"institutions":[{"id":"https://openalex.org/I874792244","display_name":"European University Institute","ror":"https://ror.org/0031wrj91","country_code":"IT","type":"education","lineage":["https://openalex.org/I874792244"]},{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesca Lagioia","raw_affiliation_strings":["CIRSFID Alma-AI, Faculty of Law, University of Bologna, Italy","European University Institute, Law Department, Italy"],"affiliations":[{"raw_affiliation_string":"CIRSFID Alma-AI, Faculty of Law, University of Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]},{"raw_affiliation_string":"European University Institute, Law Department, Italy","institution_ids":["https://openalex.org/I874792244"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Elena Consiglio","orcid":null},"institutions":[{"id":"https://openalex.org/I900890020","display_name":"University of Palermo","ror":"https://ror.org/044k9ta02","country_code":"IT","type":"education","lineage":["https://openalex.org/I900890020"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Elena Consiglio","raw_affiliation_strings":["University of Palermo, Italy"],"affiliations":[{"raw_affiliation_string":"University of Palermo, Italy","institution_ids":["https://openalex.org/I900890020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084837357","display_name":"Giovanni Sartor","orcid":"https://orcid.org/0000-0003-2210-0398"},"institutions":[{"id":"https://openalex.org/I874792244","display_name":"European University Institute","ror":"https://ror.org/0031wrj91","country_code":"IT","type":"education","lineage":["https://openalex.org/I874792244"]},{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanni Sartor","raw_affiliation_strings":["CIRSFID Alma-AI, Faculty of Law, University of Bologna, Italy","European University Institute, Law Department, Italy"],"affiliations":[{"raw_affiliation_string":"CIRSFID Alma-AI, Faculty of Law, University of Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]},{"raw_affiliation_string":"European University Institute, Law Department, Italy","institution_ids":["https://openalex.org/I874792244"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120633729","display_name":"Sara Bagnato","orcid":null},"institutions":[{"id":"https://openalex.org/I128649747","display_name":"Libera Universit\u00e0 Maria SS. Assunta","ror":"https://ror.org/02d8v0v24","country_code":"IT","type":"education","lineage":["https://openalex.org/I128649747"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sara Bagnato","raw_affiliation_strings":["University of Roma LUMSA, Italy"],"affiliations":[{"raw_affiliation_string":"University of Roma LUMSA, Italy","institution_ids":["https://openalex.org/I128649747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5120633727"],"corresponding_institution_ids":["https://openalex.org/I9360294"],"apc_list":null,"apc_paid":null,"fwci":24.2573,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.99389382,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"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":0.4413999915122986,"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":0.4413999915122986,"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":0.17919999361038208,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.07280000299215317,"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/soundness","display_name":"Soundness","score":0.7325000166893005},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.5285000205039978},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4334999918937683},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.397599995136261},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.35920000076293945},{"id":"https://openalex.org/keywords/deductive-reasoning","display_name":"Deductive reasoning","score":0.35850000381469727},{"id":"https://openalex.org/keywords/model-based-reasoning","display_name":"Model-based reasoning","score":0.3181000053882599}],"concepts":[{"id":"https://openalex.org/C39920170","wikidata":"https://www.wikidata.org/wiki/Q693083","display_name":"Soundness","level":2,"score":0.7325000166893005},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.5285000205039978},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4632999897003174},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4334999918937683},{"id":"https://openalex.org/C55587333","wikidata":"https://www.wikidata.org/wiki/Q1133029","display_name":"Engineering ethics","level":1,"score":0.39890000224113464},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.397599995136261},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.3797999918460846},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3353999853134155},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.32679998874664307},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.3181000053882599},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.30239999294281006},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.2946999967098236},{"id":"https://openalex.org/C2778049185","wikidata":"https://www.wikidata.org/wiki/Q2334719","display_name":"Legal case","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26989999413490295},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.26809999346733093},{"id":"https://openalex.org/C200635333","wikidata":"https://www.wikidata.org/wiki/Q158970","display_name":"Tort","level":3,"score":0.2669000029563904},{"id":"https://openalex.org/C21847791","wikidata":"https://www.wikidata.org/wiki/Q191081","display_name":"Logical conjunction","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.25839999318122864},{"id":"https://openalex.org/C2776325391","wikidata":"https://www.wikidata.org/wiki/Q6917865","display_name":"Motivated reasoning","level":3,"score":0.2572000026702881},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C162040827","wikidata":"https://www.wikidata.org/wiki/Q126842","display_name":"Philosophy of law","level":3,"score":0.25130000710487366}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3233/faia251579","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251579","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"pmh:oai:cadmus.eui.eu:1814/94772","is_oa":false,"landing_page_url":"https://hdl.handle.net/1814/94772","pdf_url":null,"source":{"id":"https://openalex.org/S4377196332","display_name":"Cadmus - EUI Research Repository (European University Institute)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I874792244","host_organization_name":"European University Institute","host_organization_lineage":["https://openalex.org/I874792244"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/bookPart"},{"id":"pmh:oai:cris.unibo.it:11585/1044623","is_oa":false,"landing_page_url":"https://hdl.handle.net/11585/1044623","pdf_url":null,"source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.3233/faia251579","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251579","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deploying":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"for":[5,104],"legal":[6,20,108,122],"question-answering":[7],"requires":[8],"ensuring":[9],"factual":[10],"accuracy":[11],"and":[12,37,93,114,120],"logical":[13],"coherence.":[14],"Current":[15],"evaluation":[16],"metrics":[17,68],"inadequately":[18],"capture":[19],"reasoning":[21],"complexity,":[22],"while":[23],"expert":[24,94],"assessments":[25],"lack":[26],"scalability.":[27],"We":[28],"propose":[29],"a":[30],"two-dimensional":[31],"framework":[32,97],"that":[33],"independently":[34],"measures":[35],"Truthfulness":[36],"Reasoning":[38],"Soundness":[39],"in":[40,107],"model":[41],"outputs,":[42],"applied":[43],"to":[44,70],"Italian":[45],"asylum":[46],"proceedings":[47],"requiring":[48],"evidence-based":[49],"analysis.":[50],"This":[51,99],"dual-axis":[52],"approach":[53],"reveals":[54],"critical":[55],"issues\u2014such":[56],"as":[57],"legally":[58],"correct":[59],"answers":[60],"derived":[61],"through":[62],"unsound":[63],"or":[64],"hallucinatory":[65],"reasoning\u2014that":[66],"standard":[67],"fail":[69],"detect.":[71],"To":[72],"enable":[73],"large-scale":[74],"application,":[75],"we":[76],"implement":[77],"an":[78],"automated":[79,91],"LLM-as-a-Judge":[80],"system":[81],"with":[82],"bias-mitigation":[83],"techniques.":[84],"Experimental":[85],"results":[86],"demonstrate":[87],"strong":[88],"correspondence":[89],"between":[90],"judgments":[92],"evaluations,":[95],"confirming":[96],"reliability.":[98],"work":[100],"advances":[101],"diagnostic":[102],"methodology":[103],"assessing":[105],"LLMs":[106],"domains,":[109],"offering":[110],"both":[111],"theoretical":[112],"insight":[113],"practical":[115],"applicability":[116],"toward":[117],"more":[118],"trustworthy":[119],"accountable":[121],"AI":[123],"systems.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-12-04T00:00:00"}
