{"id":"https://openalex.org/W7123616890","doi":"https://doi.org/10.1145/3769126.3769230","title":"Parameterized Argumentation-based Reasoning Tasks for Benchmarking Generative Language Models","display_name":"Parameterized Argumentation-based Reasoning Tasks for Benchmarking Generative Language Models","publication_year":2025,"publication_date":"2025-06-16","ids":{"openalex":"https://openalex.org/W7123616890","doi":"https://doi.org/10.1145/3769126.3769230"},"language":"en","primary_location":{"id":"doi:10.1145/3769126.3769230","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769126.3769230","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 Twentieth International Conference on Artificial Intelligence and Law","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3769126.3769230","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062594774","display_name":"Cor Steging","orcid":"https://orcid.org/0000-0001-6887-1687"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Cor Steging","raw_affiliation_strings":["University of Groningen, Groningen, Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-6887-1687","affiliations":[{"raw_affiliation_string":"University of Groningen, Groningen, Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056922142","display_name":"Silja Renooij","orcid":"https://orcid.org/0000-0003-4339-8146"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Silja Renooij","raw_affiliation_strings":["Utrecht University, Utrecht, Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-4339-8146","affiliations":[{"raw_affiliation_string":"Utrecht University, Utrecht, Netherlands","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060921040","display_name":"Bart Verheij","orcid":"https://orcid.org/0000-0001-8927-8751"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Bart Verheij","raw_affiliation_strings":["University of Groningen, Groningen, Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-8927-8751","affiliations":[{"raw_affiliation_string":"University of Groningen, Groningen, Netherlands","institution_ids":["https://openalex.org/I169381384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4557,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89628442,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"455","last_page":"459"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.2615000009536743,"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/T10028","display_name":"Topic Modeling","score":0.2615000009536743,"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/T13643","display_name":"Artificial Intelligence in Law","score":0.2273000031709671,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.18039999902248383,"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/generative-grammar","display_name":"Generative grammar","score":0.7595999836921692},{"id":"https://openalex.org/keywords/argument","display_name":"Argument (complex analysis)","score":0.5690000057220459},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.5594000220298767},{"id":"https://openalex.org/keywords/reasoning-system","display_name":"Reasoning system","score":0.46880000829696655},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4377000033855438},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.42329999804496765},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.421999990940094},{"id":"https://openalex.org/keywords/witness","display_name":"Witness","score":0.40959998965263367}],"concepts":[{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7595999836921692},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6883000135421753},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.5690000057220459},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.5594000220298767},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5522000193595886},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.46880000829696655},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4377000033855438},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.42329999804496765},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.421999990940094},{"id":"https://openalex.org/C2776900844","wikidata":"https://www.wikidata.org/wiki/Q8028383","display_name":"Witness","level":2,"score":0.40959998965263367},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.38199999928474426},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3221000134944916},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.31029999256134033},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2784999907016754},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.26030001044273376}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3769126.3769230","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769126.3769230","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 Twentieth International Conference on Artificial Intelligence and Law","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.rug.nl:openaire_cris_publications/77c686cc-4412-46e5-b34e-155f5c3ebf19","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/77c686cc-4412-46e5-b34e-155f5c3ebf19","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Steging, C, Renooij, S & Verheij, B 2026, Parameterized Argumentation-based Reasoning Tasks for Benchmarking Generative Language Models. in J Maranhao (ed.), 20th International Conference on Artificial Intelligence and Law, ICAIL 2025 - Proceedings of the Conference. 20th International Conference on Artificial Intelligence and Law, ICAIL 2025 - Proceedings of the Conference, Association for Computing Machinery, Inc, pp. 455-459, 20th International Conference on Artificial Intelligence and Law, ICAIL 2025, Chicago, United States, 16/06/2025. https://doi.org/10.1145/3769126.3769230","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.rug.nl:openaire/77c686cc-4412-46e5-b34e-155f5c3ebf19","is_oa":true,"landing_page_url":"https://hdl.handle.net/11370/77c686cc-4412-46e5-b34e-155f5c3ebf19","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"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":"Steging, C, Renooij, S & Verheij, B 2026, Parameterized Argumentation-based Reasoning Tasks for Benchmarking Generative Language Models. in J Maranhao (ed.), 20th International Conference on Artificial Intelligence and Law, ICAIL 2025 - Proceedings of the Conference. 20th International Conference on Artificial Intelligence and Law, ICAIL 2025 - Proceedings of the Conference, Association for Computing Machinery, Inc, pp. 455-459, 20th International Conference on Artificial Intelligence and Law, ICAIL 2025, Chicago, United States, 16/06/2025. https://doi.org/10.1145/3769126.3769230","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3769126.3769230","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769126.3769230","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 Twentieth International Conference on Artificial Intelligence and Law","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8010593056678772}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2104126268","https://openalex.org/W3022705264","https://openalex.org/W3183478923","https://openalex.org/W4309674289","https://openalex.org/W4385430086","https://openalex.org/W4385571689","https://openalex.org/W4386435222","https://openalex.org/W4386505575","https://openalex.org/W4388764805","https://openalex.org/W4400047099"],"related_works":[],"abstract_inverted_index":{"Generative":[0],"large":[1,111],"language":[2,112,174],"models":[3,25,113,148],"as":[4],"tools":[5],"in":[6,36,53,104,116],"the":[7,11,15,19,37,66,69,76,129,157,169,183,186],"legal":[8],"domain":[9],"have":[10,57],"potential":[12],"to":[13,167,178],"improve":[14],"justice":[16],"system.":[17],"However,":[18],"reasoning":[20,46,98,118,138,152,170,187],"behavior":[21],"of":[22,39,71,91,159,172,182,185,189],"current":[23],"generative":[24,173,190],"is":[26],"brittle":[27],"and":[28,41,56,86,94,131],"poorly":[29],"understood,":[30],"hence":[31],"cannot":[32],"be":[33],"responsibly":[34],"applied":[35],"domains":[38],"law":[40],"evidence.":[42],"This":[43],"paper":[44],"presents":[45],"benchmarks":[47],"that":[48,109,136],"are":[49,126,140],"dynamically":[50,82],"varied,":[51],"scalable":[52],"their":[54,132,137],"complexity,":[55,145],"formally":[58],"unambiguous":[59],"interpretations.":[60],"In":[61],"this":[62],"study,":[63],"we":[64],"illustrate":[65],"approach":[67],"on":[68,75],"basis":[70],"witness":[72,101],"testimony,":[73],"focusing":[74],"underlying":[77],"argument":[78,88],"attack":[79,89],"structure.":[80],"We":[81,107,155],"generate":[83],"both":[84],"linear":[85],"non-linear":[87],"graphs":[90],"varying":[92,165],"complexity":[93,166],"translate":[95],"these":[96,117],"into":[97],"puzzles":[99],"about":[100],"testimony":[102],"expressed":[103],"natural":[105],"language.":[106],"show":[108,156],"state-of-the-art":[110,147],"often":[114],"fail":[115],"puzzles,":[119],"already":[120],"at":[121,143],"low":[122],"complexity.":[123],"Obvious":[124],"mistakes":[125],"made":[127],"by":[128],"models,":[130,175],"inconsistent":[133],"performance":[134],"indicates":[135],"capabilities":[139,171,188],"brittle.":[141],"Furthermore,":[142],"higher":[144],"even":[146],"specifically":[149],"designed":[150],"for":[151],"make":[153],"mistakes.":[154],"viability":[158],"using":[160],"a":[161,179],"parametrized":[162],"benchmark":[163],"with":[164],"evaluate":[168],"which":[176],"contribute":[177],"better":[180],"understanding":[181],"limitations":[184],"models.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2026-01-14T00:00:00"}