{"id":"https://openalex.org/W7140136978","doi":"https://doi.org/10.18653/v1/2026.eacl-long.193","title":"Validating Automatic Evaluation of Controllable Counterspeech Generation: Rankings Matter More Than Scores","display_name":"Validating Automatic Evaluation of Controllable Counterspeech Generation: Rankings Matter More Than Scores","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140136978","doi":"https://doi.org/10.18653/v1/2026.eacl-long.193"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.eacl-long.193","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.193","pdf_url":"https://aclanthology.org/2026.eacl-long.193.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":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.eacl-long.193.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130358885","display_name":"Yi Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Zheng","raw_affiliation_strings":["Institute for Language , Cognition and Computation School of Informatics , University of Edinburgh Y"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Language , Cognition and Computation School of Informatics , University of Edinburgh Y","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088453381","display_name":"Bj\u00f6rn O. Ross","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn Ross","raw_affiliation_strings":["Institute for Language , Cognition and Computation School of Informatics , University of Edinburgh Y"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Language , Cognition and Computation School of Informatics , University of Edinburgh Y","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070783596","display_name":"Walid Magdy","orcid":"https://orcid.org/0000-0001-9676-1338"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Walid Magdy","raw_affiliation_strings":["Institute for Language , Cognition and Computation School of Informatics , University of Edinburgh Y"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Language , Cognition and Computation School of Informatics , University of Edinburgh Y","institution_ids":[]}]}],"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":0.37661677,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4131","last_page":"4146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10826","display_name":"Behavioral and Psychological Studies","score":0.032600000500679016,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10826","display_name":"Behavioral and Psychological Studies","score":0.032600000500679016,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.027799999341368675,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.027000000700354576,"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/measure","display_name":"Measure (data warehouse)","score":0.41999998688697815},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.27320000529289246},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2667999863624573},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.25949999690055847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5192000269889832},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.41999998688697815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3887999951839447},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35420000553131104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28690001368522644},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.27320000529289246},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2667999863624573},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25380000472068787},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.24770000576972961}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.eacl-long.193","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.193","pdf_url":"https://aclanthology.org/2026.eacl-long.193.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":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-long.193","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.193","pdf_url":"https://aclanthology.org/2026.eacl-long.193.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":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5122150778770447,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140136978.pdf","grobid_xml":"https://content.openalex.org/works/W7140136978.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Counterspeech":[0],"generation":[1,49,132,139],"has":[2],"emerged":[3],"as":[4,24],"a":[5,36,76,134,142],"promising":[6],"approach":[7],"to":[8,43,106,137],"combat":[9],"online":[10],"hate":[11],"speech,":[12],"with":[13],"recent":[14],"work":[15],"focusing":[16],"on":[17],"controlling":[18],"attributes":[19,29,74],"used":[20],"in":[21],"counterspeech,":[22],"such":[23,54],"strategies":[25],"or":[26],"intents.While":[27],"these":[28],"are":[30],"often":[31],"evaluated":[32],"automatically":[33],"using":[34,75],"classifiers,":[35],"key":[37],"goal":[38],"of":[39,47,53,72,97,146],"this":[40],"evaluation":[41,55,71,86,99],"is":[42,57,141],"compare":[44],"the":[45,51,60,69,95],"performance":[46],"different":[48],"models.However,":[50],"validity":[52],"results":[56,115],"questionable":[58],"when":[59,84,129],"classifiers":[61,120],"themselves":[62],"have":[63],"only":[64],"modest":[65],"performance.This":[66],"paper":[67],"examines":[68],"automatic":[70,85],"counterspeech":[73,78,131],"multi-attribute":[77],"dataset":[79],"containing":[80],"2,728":[81],"samples.We":[82],"investigate":[83],"can":[87,121],"be":[88],"trusted":[89],"for":[90,104],"model":[91,111,124],"comparison":[92],"and":[93,156],"address":[94],"limitations":[96],"current":[98],"methodologies.We":[100],"make":[101],"concrete":[102],"recommendations":[103],"how":[105],"perform":[107],"classifier":[108,113],"validation":[109,114],"before":[110],"evaluation.Our":[112],"demonstrate":[116],"that":[117,128],"even":[118],"limited":[119],"produce":[122],"trustworthy":[123],"rankings.Therefore,":[125],"we":[126],"argue":[127],"comparing":[130],"models,":[133],"classifier's":[135],"ability":[136],"rank":[138],"models":[140],"more":[143],"direct":[144],"measure":[145],"its":[147],"practical":[148],"utility":[149],"than":[150],"traditional":[151],"classification":[152],"metrics,":[153],"e.g.,":[154],"accuracy":[155],"F1.":[157]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-24T00:00:00"}
