{"id":"https://openalex.org/W4412888261","doi":"https://doi.org/10.18653/v1/2025.findings-acl.702","title":"Can Large Language Models Understand Argument Schemes?","display_name":"Can Large Language Models Understand Argument Schemes?","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888261","doi":"https://doi.org/10.18653/v1/2025.findings-acl.702"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.702","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.702","pdf_url":"https://aclanthology.org/2025.findings-acl.702.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 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.702.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038897227","display_name":"Elfia Bezou-Vrakatseli","orcid":"https://orcid.org/0009-0004-8954-246X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elfia Bezou-Vrakatseli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034045968","display_name":"Oana Cocarascu","orcid":"https://orcid.org/0000-0003-1552-8636"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oana Cocarascu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5021663592","display_name":"Sanjay Modgil","orcid":"https://orcid.org/0000-0002-7873-8086"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sanjay Modgil","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"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":0.08599086,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13666","last_page":"13681"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8100000023841858,"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":0.8100000023841858,"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":0.7458999752998352,"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/argument","display_name":"Argument (complex analysis)","score":0.7778515815734863},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7353468537330627},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3502916097640991},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.33668962121009827},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33662936091423035},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3218851387500763},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.1426641047000885}],"concepts":[{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.7778515815734863},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7353468537330627},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3502916097640991},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.33668962121009827},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33662936091423035},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3218851387500763},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.1426641047000885},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.702","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.702","pdf_url":"https://aclanthology.org/2025.findings-acl.702.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 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:kclpure.kcl.ac.uk:openaire/b2406213-1b6d-4b49-abf6-6750b0b99f7d","is_oa":true,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/b2406213-1b6d-4b49-abf6-6750b0b99f7d","pdf_url":"https://kclpure.kcl.ac.uk/ws/files/337205978/Can_Large_Language_Models_Understand_Argument_Schemes.pdf","source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"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":"Bezou Vrakatseli, E, Cocarascu, O & Modgil, S 2025, Can Large Language Models Understand Argument Schemes? in Findings of the Association for Computational Linguistics : ACL 2025 - Findings. https://doi.org/10.18653/v1/2025.findings-acl.702","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.702","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.702","pdf_url":"https://aclanthology.org/2025.findings-acl.702.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 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4269887845","display_name":null,"funder_award_id":"EP/S023356/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888261.pdf","grobid_xml":"https://content.openalex.org/works/W4412888261.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3008380943","https://openalex.org/W2115206405","https://openalex.org/W4387718383","https://openalex.org/W1528986568","https://openalex.org/W2500746363","https://openalex.org/W2062799661","https://openalex.org/W2347954438","https://openalex.org/W2071460425","https://openalex.org/W1999164976","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Argument":[0,177],"schemes":[1,27,53],"represent":[2],"stereotypical":[3],"patterns":[4],"of":[5,45,116],"reasoning":[6,127],"that":[7,18,94],"occur":[8],"in":[9,36,62,101,118,129],"everyday":[10],"arguments.However,":[11],"despite":[12],"their":[13],"usefulness,":[14],"argument":[15,52,103,120],"scheme":[16],"classification,":[17],"is":[19,32,137,183,193,196,207,210,221],"classifying":[20,51],"natural":[21],"language":[22,47],"arguments":[23],"according":[24],"to":[25,72,199,201,213,216],"the":[26,112],"they":[28],"are":[29],"instances":[30],"of,":[31],"an":[33],"underexplored":[34],"task":[35,74],"NLP.In":[37],"this":[38,154],"paper":[39],"we":[40],"present":[41],"a":[42,157,197,211,222],"systematic":[43],"evaluation":[44],"large":[46],"models":[48,97],"(LLMs)":[49],"for":[50,107,125],"based":[54],"on":[55,83],"Walton's":[56],"taxonomy.We":[57],"experiment":[58],"with":[59],"seven":[60],"LLMs":[61,117],"zero-shot,":[63],"few-shot,":[64],"and":[65,68,79,87,122,161],"chain-of-thought":[66],"prompting,":[67],"explore":[69],"two":[70],"strategies":[71],"enhance":[73],"instructions:":[75],"employing":[76],"formal":[77],"definitions":[78],"LLM-generated":[80],"descriptions.Our":[81],"analysis":[82],"both":[84],"manually":[85],"annotated":[86],"automatically":[88],"generated":[89],"arguments,":[90],"including":[91],"enthymemes,":[92],"indicates":[93],"while":[95],"larger":[96],"exhibit":[98],"satisfactory":[99],"performance":[100],"identifying":[102,119],"schemes,":[104,121],"challenges":[105],"remain":[106],"smaller":[108],"models.Our":[109],"work":[110],"offers":[111],"first":[113],"comprehensive":[114],"assessment":[115],"provides":[123],"insights":[124],"advancing":[126],"capabilities":[128],"computational":[130],"argumentation.Argument":[131],"from":[132,150,178],"Consequences":[133],"P:":[134,152],"If":[135,191,205],"A":[136,144],"brought":[138,148],"about,":[139],"good/bad":[140],"consequences":[141],"occur.C:":[142],"Therefore,":[143],"should":[145],"(not)":[146],"be":[147],"about.Argument":[149],"Example":[151],"In":[153],"particular":[155],"case,":[156],"has":[158,168,175],"properties":[159],"F":[160,170],"G.":[162,176,203,218],"C:":[163,219],"So,":[164],"generally,":[165],"if":[166],"x":[167],"property":[169],",":[171],"then":[172],"it":[173,195,209],"also":[174],"Values":[179],"P1:":[180],"Value":[181],"V":[182,192,206,220],"positive/negative":[184],"as":[185],"judged":[186],"by":[187],"agent":[188],"a.":[189],"P2:":[190],"positive":[194],"reason":[198,212],"commit":[200,215],"goal":[202,217],"P2':":[204],"negative":[208],"not":[214]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}