{"id":"https://openalex.org/W7140126496","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.194","title":"MultiCW: A Large-Scale Balanced Benchmark Dataset for Training Robust Check-Worthiness Detection Models","display_name":"MultiCW: A Large-Scale Balanced Benchmark Dataset for Training Robust Check-Worthiness Detection Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140126496","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.194"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.194","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.194","pdf_url":"https://aclanthology.org/2026.findings-eacl.194.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: EACL 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-eacl.194.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066547439","display_name":"Martin Hyben","orcid":"https://orcid.org/0000-0001-5314-1358"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin Hyben","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030621800","display_name":"Sebastian Kula","orcid":"https://orcid.org/0000-0001-7559-6046"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sebastian Kula","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081841143","display_name":"J\u00e1n \u010cegi\u0148","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan Cegin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043199710","display_name":"Jakub \u0160imko","orcid":"https://orcid.org/0000-0003-0239-4237"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jakub Simko","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082763244","display_name":"Ivan Srba","orcid":"https://orcid.org/0000-0003-3511-5337"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ivan Srba","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032021797","display_name":"R\u00f3bert M\u00f3ro","orcid":"https://orcid.org/0000-0002-3052-8290"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robert Moro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.2497321,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3737","last_page":"3754"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.2515000104904175,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.2515000104904175,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.07490000128746033,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.04969999939203262,"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/training","display_name":"Training (meteorology)","score":0.6187000274658203},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.499099999666214},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41659998893737793},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3409000039100647},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.3246999979019165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6212999820709229},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6187000274658203},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5116000175476074},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.499099999666214},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41659998893737793},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40549999475479126},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4047999978065491},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3409000039100647},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3246999979019165},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25839999318122864}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.194","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.194","pdf_url":"https://aclanthology.org/2026.findings-eacl.194.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: EACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:zenodo.org:19403824","is_oa":true,"landing_page_url":"https://arxiv.org/abs/arXiv:2602.16298","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"EACL 2026, Findings of the Association for Computational Linguistics, Rabat, Morocco","raw_type":"info:eu-repo/semantics/other"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.194","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.194","pdf_url":"https://aclanthology.org/2026.findings-eacl.194.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: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Climate action","score":0.4099935293197632,"id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140126496.pdf","grobid_xml":"https://content.openalex.org/works/W7140126496.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"are":[4],"beginning":[5],"to":[6],"reshape":[7],"how":[8],"media":[9],"professionals":[10],"verify":[11],"information,":[12],"yet":[13],"automated":[14,143],"support":[15],"for":[16,36,141],"detecting":[17],"check-worthy":[18,37,67,157],"claims-a":[19],"key":[20],"step":[21],"in":[22,88],"the":[23,28,156],"fact-checking":[24,144],"process-remains":[25],"limited.We":[26],"introduce":[27,78],"Multi-Check-Worthy":[29],"(Mul-tiCW)":[30],"dataset,":[31],"a":[32,102,137],"balanced":[33,64,81],"multilingual":[34,99,139],"benchmark":[35,95],"claim":[38,124,158],"detection":[39,159],"spanning":[40],"16":[41],"languages,":[42,132],"7":[43],"topical":[44],"domains,":[45,133],"and":[46,59,68,108,126,134,145,152],"2":[47],"writing":[48],"styles.It":[49],"consists":[50],"of":[51,66,85,105],"123,722":[52],"samples,":[53],"evenly":[54],"distributed":[55],"between":[56,149],"noisy":[57],"(informal)":[58],"structured":[60],"(formal)":[61],"texts,":[62],"with":[63],"representation":[65],"noncheck-worthy":[69],"classes":[70],"across":[71,131],"all":[72],"languages.To":[73,91],"probe":[74],"robustness,":[75],"we":[76,94],"also":[77],"an":[79],"equally":[80],"out-of-distribution":[82,129],"evaluation":[83],"set":[84,104],"27,761":[86],"samples":[87],"4":[89],"additional":[90],"provide":[92],"baselines,":[93],"3":[96],"common":[97],"fine-tuned":[98,117],"transformers":[100],"against":[101],"diverse":[103],"15":[106],"commercial":[107],"open":[109],"LLMs":[110,122,154],"under":[111],"zero-shot":[112,121],"settings.Our":[113],"findings":[114],"show":[115,127],"that":[116],"models":[118,151],"consistently":[119],"outperform":[120],"on":[123,155],"classification":[125],"strong":[128],"generalization":[130],"styles.Mul-tiCW":[135],"provides":[136],"rigorous":[138],"resource":[140],"advancing":[142],"enables":[146],"systematic":[147],"comparisons":[148],"finetuned":[150],"cutting-edge":[153],"task.":[160]},"counts_by_year":[],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2026-02-24T00:00:00"}