{"id":"https://openalex.org/W7166832669","doi":"https://doi.org/10.18653/v1/2026.acl-long.1000","title":"Benchmarking Large Vision-Language Models on CFMME: A Comprehensive Chinese Financial Multimodal Evaluation Dataset","display_name":"Benchmarking Large Vision-Language Models on CFMME: A Comprehensive Chinese Financial Multimodal Evaluation Dataset","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166832669","doi":"https://doi.org/10.18653/v1/2026.acl-long.1000"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1000","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1000","pdf_url":"https://aclanthology.org/2026.acl-long.1000.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1000.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139835546","display_name":"Qian Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139852182","display_name":"Xianyin Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xianyin Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139814010","display_name":"Yanzhi Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanzhi Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139745822","display_name":"Lifan Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lifan Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139797253","display_name":"Feng Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139749506","display_name":"Chi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chi Zhang","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":0.86775982,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21902","last_page":"21919"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.11129999905824661,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.11129999905824661,"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/T11326","display_name":"Stock Market Forecasting Methods","score":0.09480000287294388,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.04230000078678131,"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/benchmarking","display_name":"Benchmarking","score":0.6790000200271606},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.3961000144481659},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2921000123023987},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.2883000075817108}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6790000200271606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5174000263214111},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3961000144481659},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.36169999837875366},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.33799999952316284},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32429999113082886},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28119999170303345},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1000","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1000","pdf_url":"https://aclanthology.org/2026.acl-long.1000.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1000","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1000","pdf_url":"https://aclanthology.org/2026.acl-long.1000.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166832669.pdf","grobid_xml":"https://content.openalex.org/works/W7166832669.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"emergence":[1],"of":[2,29,41,91,104,115,138],"Large":[3],"Vision-Language":[4],"Models":[5],"(LVLMs)":[6],"has":[7],"substantially":[8],"expanded":[9],"model":[10,99],"capabilities":[11,40],"beyond":[12],"text-only":[13],"understanding,":[14,36],"enabling":[15],"unified":[16],"inference":[17],"across":[18],"both":[19],"visual":[20],"and":[21,24,38,80,111,121,143],"textual":[22],"modalities":[23,79],"supporting":[25],"a":[26,55,88],"broader":[27],"range":[28],"real-world":[30],"applications.To":[31],"comprehensively":[32],"evaluate":[33],"the":[34,44,97,107,118,171],"perception,":[35],"reasoning,":[37],"cognition":[39],"LVLMs":[42],"throughout":[43],"entire":[45],"financial":[46,58,77,172],"business":[47],"workflow":[48],"in":[49,130,159,170],"Chinese":[50,57],"contexts,":[51],"we":[52,86,134],"introduce":[53],"CFMME,":[54,85],"novel":[56],"multimodal":[59,83,168],"evaluation":[60,90],"benchmark.CFMME":[61],"comprises":[62],"6,052":[63],"instances":[64],"spanning":[65],"from":[66],"fundamental":[67],"academic":[68],"knowledge":[69],"to":[70],"complex":[71],"realworld":[72],"applications,":[73],"covering":[74],"eight":[75],"primary":[76],"image":[78],"four":[81],"core":[82],"tasks.On":[84],"conduct":[87,135],"thorough":[89],"representative":[92],"LVLMs.The":[93],"results":[94],"show":[95],"that":[96,153],"state-of-the-art":[98],"attains":[100],"an":[101,112],"overall":[102],"accuracy":[103],"66.11%":[105],"on":[106,117,166],"question":[108],"answering":[109],"task":[110],"average":[113],"score":[114],"77.18":[116],"detection,":[119],"recognition,":[120],"information":[122],"extraction":[123],"tasks,":[124],"indicating":[125],"substantial":[126],"room":[127],"for":[128,149],"improvement":[129],"current":[131],"LVLMs.In":[132],"addition,":[133],"detailed":[136],"analyses":[137],"error":[139],"causes,":[140],"cross-modal":[141],"capabilities,":[142],"multiorientation":[144],"settings,":[145],"yielding":[146],"valuable":[147],"insights":[148],"future":[150],"research.We":[151],"hope":[152],"CFMME":[154],"will":[155],"spur":[156],"further":[157],"progress":[158],"LVLMs,":[160],"especially":[161],"by":[162],"improving":[163],"their":[164],"performance":[165],"multiple":[167],"tasks":[169],"domain.":[173],"Benchmarks":[174]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}