{"id":"https://openalex.org/W4412944729","doi":"https://doi.org/10.18653/v1/2025.acl-long.1164","title":"Limited Generalizability in Argument Mining: State-Of-The-Art Models Learn Datasets, Not Arguments","display_name":"Limited Generalizability in Argument Mining: State-Of-The-Art Models Learn Datasets, Not Arguments","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944729","doi":"https://doi.org/10.18653/v1/2025.acl-long.1164"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1164","doi":"https://doi.org/10.18653/v1/2025.acl-long.1164","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1164","pdf_url":"https://aclanthology.org/2025.acl-long.1164.pdf","source":{"id":"https://openalex.org/S4363608652","display_name":"Annual Meeting of the Association for Computational Linguistics (ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2025.acl-long.1164.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028722230","display_name":"Marc Feger","orcid":"https://orcid.org/0009-0008-6385-1722","observed_orcids":["https://orcid.org/0009-0008-6385-1722"]},"institutions":[{"id":"https://openalex.org/I44260953","display_name":"Heinrich Heine University D\u00fcsseldorf","ror":"https://ror.org/024z2rq82","country_code":"DE","type":"education","lineage":["https://openalex.org/I44260953"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marc Feger","raw_affiliation_strings":["Heinrich-Heine-University D\u00fcsseldorf , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Heinrich-Heine-University D\u00fcsseldorf , Germany","institution_ids":["https://openalex.org/I44260953"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086954858","display_name":"Katarina Boland","orcid":"https://orcid.org/0000-0003-2958-9712","observed_orcids":["https://orcid.org/0000-0003-2958-9712"]},"institutions":[{"id":"https://openalex.org/I44260953","display_name":"Heinrich Heine University D\u00fcsseldorf","ror":"https://ror.org/024z2rq82","country_code":"DE","type":"education","lineage":["https://openalex.org/I44260953"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Katarina Boland","raw_affiliation_strings":["Heinrich-Heine-University D\u00fcsseldorf , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Heinrich-Heine-University D\u00fcsseldorf , Germany","institution_ids":["https://openalex.org/I44260953"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070728314","display_name":"Stefan Dietze","orcid":"https://orcid.org/0009-0001-4364-9243","observed_orcids":["https://orcid.org/0009-0001-4364-9243"]},"institutions":[{"id":"https://openalex.org/I4210101898","display_name":"GESIS - Leibniz Institute for the Social Sciences","ror":"https://ror.org/018afyw53","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I4210101898"]},{"id":"https://openalex.org/I44260953","display_name":"Heinrich Heine University D\u00fcsseldorf","ror":"https://ror.org/024z2rq82","country_code":"DE","type":"education","lineage":["https://openalex.org/I44260953"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Dietze","raw_affiliation_strings":["GESIS -Leibniz Institute for the Social Sciences & Heinrich-Heine-University D\u00fcsseldorf , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GESIS -Leibniz Institute for the Social Sciences & Heinrich-Heine-University D\u00fcsseldorf , Germany","institution_ids":["https://openalex.org/I4210101898","https://openalex.org/I44260953"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0171,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.8641198,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"23900","last_page":"23915"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.5889000296592712,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.5889000296592712,"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/T10028","display_name":"Topic Modeling","score":0.27489998936653137,"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/T12119","display_name":"Linguistics and Discourse Analysis","score":0.041999999433755875,"subfield":{"id":"https://openalex.org/subfields/1211","display_name":"Philosophy"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/argument-mining","display_name":"argument mining","score":0.9860000014305115},{"id":"https://openalex.org/keywords/argument-identification","display_name":"argument identification","score":0.8410000205039978},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.6909999847412109},{"id":"https://openalex.org/keywords/bert","display_name":"BERT","score":0.42800000309944153},{"id":"https://openalex.org/keywords/contrastive-pretraining","display_name":"contrastive pre-training","score":0.8619999885559082},{"id":"https://openalex.org/keywords/discourse-analysis","display_name":"discourse analysis","score":0.6079999804496765}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.9126698970794678},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.791296124458313},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5777624845504761},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5188902020454407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39745575189590454},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.37869131565093994},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.353083074092865},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.341539204120636},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.3335299491882324},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1893324851989746},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.17638131976127625},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17541608214378357},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.16655674576759338},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1164","doi":"https://doi.org/10.18653/v1/2025.acl-long.1164","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1164","pdf_url":"https://aclanthology.org/2025.acl-long.1164.pdf","source":{"id":"https://openalex.org/S4363608652","display_name":"Annual Meeting of the Association for Computational Linguistics (ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.22137","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.22137","pdf_url":"https://arxiv.org/pdf/2505.22137","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":"doi:10.48550/arxiv.2505.22137","doi":"https://doi.org/10.48550/arxiv.2505.22137","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.22137","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.1164","doi":"https://doi.org/10.18653/v1/2025.acl-long.1164","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1164","pdf_url":"https://aclanthology.org/2025.acl-long.1164.pdf","source":{"id":"https://openalex.org/S4363608652","display_name":"Annual Meeting of the Association for Computational Linguistics (ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944729.pdf","grobid_xml":"https://content.openalex.org/works/W4412944729.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W2413243053","https://openalex.org/W410723623","https://openalex.org/W2015341305","https://openalex.org/W2035068594","https://openalex.org/W4225593417","https://openalex.org/W2573498121","https://openalex.org/W3022298670","https://openalex.org/W3160494304","https://openalex.org/W2388888344"],"abstract_inverted_index":{"Identifying":[0],"arguments":[1],"is":[2],"a":[3,35,48,88],"necessary":[4],"prerequisite":[5],"for":[6,110],"various":[7],"tasks":[8],"in":[9,29,96,185],"automated":[10],"discourse":[11],"analysis,":[12],"particularly":[13],"within":[14],"contexts":[15,74],"such":[16,67,84],"as":[17,118],"political":[18],"debates,":[19],"online":[20],"discussions,":[21],"and":[22,104,179,189],"scientific":[23],"reasoning.In":[24],"addition":[25],"to":[26,94,121,127,133,139,172],"theoretical":[27],"advances":[28],"understanding":[30],"the":[31,64,79,122,158],"constitution":[32],"of":[33,38,51,75,83],"arguments,":[34],"significant":[36],"body":[37],"research":[39],"has":[40],"emerged":[41],"around":[42],"practical":[43],"argument":[44],"mining,":[45],"supported":[46],"by":[47,150],"growing":[49],"number":[50],"publicly":[52],"available":[53],"datasets.On":[54],"these":[55,130],"benchmarks,":[56,165],"BERT-like":[57],"transformers":[58],"have":[59],"consistently":[60],"performed":[61],"best,":[62],"reinforcing":[63],"belief":[65],"that":[66,143],"models":[68,131,159],"are":[69],"broadly":[70],"applicable":[71],"across":[72],"diverse":[73],"debate.This":[76],"study":[77],"offers":[78],"first":[80],"large-scale":[81],"re-evaluation":[82],"state-of-theart":[85],"models,":[86],"with":[87,107],"specific":[89],"focus":[90],"on":[91,113,135,163],"their":[92,166],"ability":[93],"generalize":[95],"identifying":[97],"arguments.We":[98],"evaluate":[99],"four":[100],"transformers,":[101],"three":[102],"standard":[103],"one":[105],"enhanced":[106],"contrastive":[108],"pre-training":[109,178],"better":[111],"generalization,":[112],"17":[114],"English":[115],"sentence-level":[116],"datasets":[117],"most":[119],"relevant":[120],"task.Our":[123],"findings":[124],"show":[125],"that,":[126],"varying":[128],"degrees,":[129],"tend":[132],"rely":[134],"lexical":[136],"shortcuts":[137],"tied":[138],"content":[140],"words,":[141],"suggesting":[142],"apparent":[144],"progress":[145],"may":[146],"often":[147],"be":[148],"driven":[149],"dataset-specific":[151],"cues":[152],"rather":[153],"than":[154],"true":[155],"task":[156],"alignment.While":[157],"achieve":[160],"strong":[161],"results":[162],"familiar":[164],"performance":[167],"drops":[168],"markedly":[169],"when":[170],"applied":[171],"unseen":[173],"datasets.Nonetheless,":[174],"incorporating":[175],"both":[176,187],"task-specific":[177],"joint":[180],"benchmark":[181],"training":[182],"proves":[183],"effective":[184],"enhancing":[186],"robustness":[188],"generalization.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-10T00:00:00"}