{"id":"https://openalex.org/W7166848046","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1328","title":"OpenExempt: A Diagnostic Benchmark for Legal Reasoning and a Framework for Creating Custom Benchmarks on Demand","display_name":"OpenExempt: A Diagnostic Benchmark for Legal Reasoning and a Framework for Creating Custom Benchmarks on Demand","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166848046","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1328"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1328","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1328","pdf_url":"https://aclanthology.org/2026.findings-acl.1328.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1328.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033224240","display_name":"Sergio Servantez","orcid":"https://orcid.org/0000-0002-8294-0279"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sergio Servantez","raw_affiliation_strings":["Northwestern University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075418086","display_name":"Sarah B. Lawsky","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarah B. Lawsky","raw_affiliation_strings":["University of Illinois Urbana-Champaign \u2020Corresponding"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign \u2020Corresponding","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123501680","display_name":"Rajiv Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajiv Jain","raw_affiliation_strings":["Adobe Research ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research ,","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139775668","display_name":"Daniel W. Linna Jr.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel W. Linna Jr.","raw_affiliation_strings":["Northwestern University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University ,","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114000097","display_name":"Kristian J. Hammond","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kristian J Hammond","raw_affiliation_strings":["Northwestern University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University ,","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.80983598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"26644","last_page":"26669"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.19040000438690186,"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"}},"topics":[{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.19040000438690186,"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/T13972","display_name":"Business Law and Ethics","score":0.09780000150203705,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.07440000027418137,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5339000225067139},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.3792000114917755},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3352999985218048},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.2858000099658966},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.2786000072956085},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.26499998569488525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6460000276565552},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5339000225067139},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.3792000114917755},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.36250001192092896},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32089999318122864},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2827000021934509},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.2818000018596649},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2680000066757202},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.25870001316070557},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.2583000063896179},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1328","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1328","pdf_url":"https://aclanthology.org/2026.findings-acl.1328.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1328","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1328","pdf_url":"https://aclanthology.org/2026.findings-acl.1328.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5914642810821533,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166848046.pdf","grobid_xml":"https://content.openalex.org/works/W7166848046.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reasoning":[0],"benchmarks":[1,50],"have":[2],"played":[3],"a":[4,16,25,33,68,92,131],"crucial":[5],"role":[6],"in":[7,41,122,167],"the":[8,128,168,174,187],"progress":[9],"of":[10,27,75,84,95,170,190],"language":[11,97,153],"models.Yet":[12],"rigorous":[13],"evaluation":[14,74,142],"remains":[15],"significant":[17],"challenge":[18],"as":[19,46],"static":[20],"question-answer":[21],"pairs":[22],"provide":[23],"only":[24,161],"snapshot":[26],"performance,":[28],"compressing":[29],"complex":[30],"behavior":[31],"into":[32],"single":[34],"accuracy":[35],"metric.This":[36],"limitation":[37],"is":[38],"especially":[39],"true":[40],"complex,":[42],"rule-bound":[43],"domains":[44],"such":[45],"law,":[47],"where":[48],"existing":[49],"are":[51],"costly":[52],"to":[53,89,119,145,179],"build":[54],"and":[55,70,100,113,166,176,185],"ill":[56],"suited":[57],"for":[58,72,134],"isolating":[59],"specific":[60],"failure":[61],"modes.To":[62],"address":[63],"this,":[64],"we":[65,126],"introduce":[66],"OpenExempt,":[67],"framework":[69,175],"benchmark":[71,133,177],"diagnostic":[73,132],"legal":[76,135],"reasoning.The":[77],"OpenExempt":[78,129],"Framework":[79],"uses":[80],"expert-crafted":[81],"symbolic":[82],"representations":[83],"U.S.":[85],"Bankruptcy":[86],"Code":[87],"statutes":[88],"dynamically":[90],"generate":[91],"large":[93],"space":[94],"natural":[96],"reasoning":[98,117,136,164,191],"tasks":[99],"their":[101],"machinecomputable":[102],"solutions":[103],"on":[104,150],"demand.This":[105],"gives":[106],"users":[107],"fine-grained":[108],"control":[109],"over":[110],"task":[111],"complexity":[112],"scope,":[114],"allowing":[115],"individual":[116],"skills":[118],"be":[120],"probed":[121],"isolation.Using":[123],"this":[124],"system,":[125],"construct":[127],"Benchmark,":[130],"with":[137],"9,765":[138],"samples":[139],"across":[140],"nine":[141],"suites":[143],"designed":[144],"carefully":[146],"probe":[147],"model":[148],"capabilities.Experiments":[149],"13":[151],"diverse":[152],"models":[154],"reveal":[155],"sharp":[156],"performance":[157],"cliffs":[158],"that":[159],"emerge":[160],"under":[162],"longer":[163],"paths":[165],"presence":[169],"obfuscating":[171],"statements.We":[172],"release":[173],"publicly":[178],"support":[180],"research":[181],"aimed":[182],"at":[183],"understanding":[184],"improving":[186],"next":[188],"generation":[189],"systems.":[192]},"counts_by_year":[],"updated_date":"2026-08-24T07:32:12.397491","created_date":"2026-07-02T00:00:00"}