{"id":"https://openalex.org/W7166888017","doi":"https://doi.org/10.18653/v1/2026.findings-acl.275","title":"K-MetBench: A Multi-Dimensional Benchmark for Fine-Grained Evaluation of Expert Reasoning, Locality, and Multimodality in Meteorology","display_name":"K-MetBench: A Multi-Dimensional Benchmark for Fine-Grained Evaluation of Expert Reasoning, Locality, and Multimodality in Meteorology","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166888017","doi":"https://doi.org/10.18653/v1/2026.findings-acl.275"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.275","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.275","pdf_url":"https://aclanthology.org/2026.findings-acl.275.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 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-acl.275.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139848444","display_name":"Soyeon Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I3131980609","display_name":"Korean Academy of Science and Technology","ror":"https://ror.org/01j49yd81","country_code":"KR","type":"education","lineage":["https://openalex.org/I3131980609"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soyeon Kim","raw_affiliation_strings":["KAIST , INEEJI Seongnam , Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST , INEEJI Seongnam , Korea","institution_ids":["https://openalex.org/I3131980609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057564773","display_name":"Cheongwoong Kang","orcid":"https://orcid.org/0000-0002-1285-9694"},"institutions":[{"id":"https://openalex.org/I3131980609","display_name":"Korean Academy of Science and Technology","ror":"https://ror.org/01j49yd81","country_code":"KR","type":"education","lineage":["https://openalex.org/I3131980609"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Cheongwoong Kang","raw_affiliation_strings":["KAIST Seongnam , Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST Seongnam , Korea","institution_ids":["https://openalex.org/I3131980609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134760164","display_name":"Myeongjin Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I3131980609","display_name":"Korean Academy of Science and Technology","ror":"https://ror.org/01j49yd81","country_code":"KR","type":"education","lineage":["https://openalex.org/I3131980609"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Myeongjin Lee","raw_affiliation_strings":["KAIST Seongnam , Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST Seongnam , Korea","institution_ids":["https://openalex.org/I3131980609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013569488","display_name":"Eun\u2010Chul Chang","orcid":"https://orcid.org/0000-0002-5784-447X"},"institutions":[{"id":"https://openalex.org/I206597221","display_name":"Kongju National University","ror":"https://ror.org/0373nm262","country_code":"KR","type":"education","lineage":["https://openalex.org/I206597221"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Eun-Chul Chang","raw_affiliation_strings":["Kongju National University Gongju , Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kongju National University Gongju , Korea","institution_ids":["https://openalex.org/I206597221"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098329974","display_name":"Lee JaeDeok","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee Jaedeok","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139782486","display_name":"Jaesik Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I3131980609","display_name":"Korean Academy of Science and Technology","ror":"https://ror.org/01j49yd81","country_code":"KR","type":"education","lineage":["https://openalex.org/I3131980609"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaesik Choi","raw_affiliation_strings":["KAIST , INEEJI Seongnam , Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST , INEEJI Seongnam , Korea","institution_ids":["https://openalex.org/I3131980609"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.84353261,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5574","last_page":"5612"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.17470000684261322,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.17470000684261322,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10799","display_name":"Data Visualization and Analytics","score":0.07699999958276749,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.0575999990105629,"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/multimodality","display_name":"Multimodality","score":0.7001000046730042},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6104000210762024},{"id":"https://openalex.org/keywords/expert-system","display_name":"Expert system","score":0.47850000858306885},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2328999936580658}],"concepts":[{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.7001000046730042},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6104000210762024},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5421000123023987},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.47850000858306885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3156000077724457},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28630000352859497},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.2793999910354614},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.26260000467300415},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2328999936580658},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.22990000247955322}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.275","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.275","pdf_url":"https://aclanthology.org/2026.findings-acl.275.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 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.275","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.275","pdf_url":"https://aclanthology.org/2026.findings-acl.275.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 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.8742871880531311,"display_name":"Climate action"}],"awards":[{"id":"https://openalex.org/G2989752301","display_name":null,"funder_award_id":"KMA2021-00123","funder_id":"https://openalex.org/F4320322036","funder_display_name":"Korea Meteorological Administration"},{"id":"https://openalex.org/G3736587842","display_name":null,"funder_award_id":"RS-2019-II190075","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4468082379","display_name":null,"funder_award_id":"RS-2019-II190075","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G6435501467","display_name":null,"funder_award_id":"RS-2022-II220984","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G8212511589","display_name":null,"funder_award_id":"RS-2022-II220984","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320322036","display_name":"Korea Meteorological Administration","ror":"https://ror.org/04nrmrg07"},{"id":"https://openalex.org/F4320322065","display_name":"National IT Industry Promotion Agency","ror":"https://ror.org/026v53e29"},{"id":"https://openalex.org/F4320324161","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63"},{"id":"https://openalex.org/F4320327249","display_name":"National Institute of Meteorological Sciences","ror":"https://ror.org/04m2hj141"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320334904","display_name":"National Institute for Materials Science","ror":"https://ror.org/026v1ze26"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166888017.pdf","grobid_xml":"https://content.openalex.org/works/W7166888017.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"development":[1],"of":[2,18,50,65],"practical":[3],"(multimodal)":[4],"large":[5],"language":[6],"model":[7],"assistants":[8],"for":[9,111],"Korean":[10,88],"weather":[11],"forecasters":[12],"is":[13,120],"hindered":[14],"by":[15],"the":[16],"absence":[17],"a":[19,33,69,78,109],"multidimensional,":[20],"expert-level":[21],"evaluation":[22,64],"framework":[23],"grounded":[24,36],"in":[25,37,73,95],"authoritative":[26],"sources.To":[27],"address":[28],"this,":[29],"we":[30],"introduce":[31],"K-MetBench,":[32],"diagnostic":[34],"benchmark":[35],"national":[38],"qualification":[39],"exams.It":[40],"exposes":[41],"critical":[42],"gaps":[43],"across":[44],"four":[45],"dimensions:":[46],"expert":[47,116],"visual":[48],"reasoning":[49,79],"charts,":[51],"logical":[52],"validity":[53],"via":[54],"expert-verified":[55],"rationales,":[56],"Korean-specific":[57],"geocultural":[58],"comprehension,":[59],"and":[60,77],"fine-grained":[61],"domain":[62],"analysis.Our":[63],"55":[66],"models":[67,82,89,94],"reveals":[68],"profound":[70],"modality":[71],"gap":[72,80],"interpreting":[74],"specialized":[75],"diagrams":[76],"where":[81],"hallucinate":[83],"logic":[84],"despite":[85],"correct":[86],"predictions.Crucially,":[87],"outperform":[90],"significantly":[91],"larger":[92],"global":[93],"local":[96],"contexts,":[97],"demonstrating":[98],"that":[99],"parameter":[100],"scaling":[101],"alone":[102],"cannot":[103],"resolve":[104],"cultural":[105],"dependencies.K-MetBench":[106],"serves":[107],"as":[108],"roadmap":[110],"developing":[112],"reliable,":[113],"culturally":[114],"aware":[115],"AI":[117],"agents.The":[118],"dataset":[119],"available":[121],"at":[122],"https://huggingface.co/":[123],"datasets/soyeonbot/K-MetBench.OpenAI.2025.":[124]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-07-02T00:00:00"}
