{"id":"https://openalex.org/W4414991998","doi":"https://doi.org/10.48550/arxiv.2508.13491","title":"From Scores to Skills: A Cognitive Diagnosis Framework for Evaluating Financial Large Language Models","display_name":"From Scores to Skills: A Cognitive Diagnosis Framework for Evaluating Financial Large Language Models","publication_year":2025,"publication_date":"2025-08-19","ids":{"openalex":"https://openalex.org/W4414991998","doi":"https://doi.org/10.48550/arxiv.2508.13491"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2508.13491","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.13491","pdf_url":"https://arxiv.org/pdf/2508.13491","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.13491","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110247102","display_name":"Ziyan Kuang","orcid":"https://orcid.org/0009-0009-4725-8520","observed_orcids":["https://orcid.org/0009-0009-4725-8520"]},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kuang, Ziyan","raw_affiliation_strings":["Center for the Study of Language and Information , Wuhan University","School of Artifical Intelligence , Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for the Study of Language and Information , Wuhan University","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Artifical Intelligence , Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101124710","display_name":"Feiyu Zhu","orcid":"https://orcid.org/0009-0007-0232-6601","observed_orcids":["https://orcid.org/0009-0007-0232-6601","https://orcid.org/0009-0006-3136-0406"]},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhu, Feiyu","raw_affiliation_strings":["Center for the Study of Language and Information , Wuhan University","School of Artifical Intelligence , Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for the Study of Language and Information , Wuhan University","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Artifical Intelligence , Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102679407","display_name":"Maowei Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I206777745","display_name":"Nanjing Audit University","ror":"https://ror.org/04zj2bd87","country_code":"CN","type":"education","lineage":["https://openalex.org/I206777745"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang, Maowei","raw_affiliation_strings":["School of Computer Science , Nanjing Audit University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Nanjing Audit University","institution_ids":["https://openalex.org/I206777745"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029848442","display_name":"Yanzhao Lai","orcid":"https://orcid.org/0000-0002-8067-0842","observed_orcids":["https://orcid.org/0000-0002-8067-0842","https://orcid.org/0009-0002-1625-9693"]},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lai, Yanzhao","raw_affiliation_strings":["Southwest Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest Jiaotong University","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089200131","display_name":"Zelin Wang","orcid":"https://orcid.org/0009-0001-4430-5151","observed_orcids":["https://orcid.org/0009-0001-4430-5151"]},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4405280177","display_name":"Beijing University of Financial Technology","ror":"https://ror.org/02hwff938","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405280177"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Zelin","raw_affiliation_strings":["Beijing University of Financial Technology","Center for the Study of Language and Information , Wuhan University","School of Artifical Intelligence , Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Financial Technology","institution_ids":["https://openalex.org/I4405280177"]},{"raw_affiliation_string":"Center for the Study of Language and Information , Wuhan University","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Artifical Intelligence , Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Zhitong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4405280177","display_name":"Beijing University of Financial Technology","ror":"https://ror.org/02hwff938","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405280177"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Zhitong","raw_affiliation_strings":["Beijing University of Financial Technology","Center for the Study of Language and Information , Wuhan University","School of Artifical Intelligence , Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Financial Technology","institution_ids":["https://openalex.org/I4405280177"]},{"raw_affiliation_string":"Center for the Study of Language and Information , Wuhan University","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Artifical Intelligence , Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083330935","display_name":"Meikang Qiu","orcid":"https://orcid.org/0000-0002-1004-0140","observed_orcids":["https://orcid.org/0000-0002-1004-0140"]},"institutions":[{"id":"https://openalex.org/I25041050","display_name":"Augusta University","ror":"https://ror.org/012mef835","country_code":"US","type":"education","lineage":["https://openalex.org/I25041050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiu, Meikang","raw_affiliation_strings":["Computer and Cyber Sciences , Augusta University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer and Cyber Sciences , Augusta University","institution_ids":["https://openalex.org/I25041050"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112641253","display_name":"Jiajia Huang","orcid":"https://orcid.org/0009-0009-9050-0781","observed_orcids":["https://orcid.org/0009-0009-9050-0781"]},"institutions":[{"id":"https://openalex.org/I206777745","display_name":"Nanjing Audit University","ror":"https://ror.org/04zj2bd87","country_code":"CN","type":"education","lineage":["https://openalex.org/I206777745"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Jiajia","raw_affiliation_strings":["School of Computer Science , Nanjing Audit University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Nanjing Audit University","institution_ids":["https://openalex.org/I206777745"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102012008","display_name":"Min Peng","orcid":"https://orcid.org/0000-0001-7445-5567","observed_orcids":["https://orcid.org/0000-0001-7445-5567"]},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng, Min","raw_affiliation_strings":["Center for the Study of Language and Information , Wuhan University","School of Artifical Intelligence , Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for the Study of Language and Information , Wuhan University","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Artifical Intelligence , Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101868563","display_name":"Qianqian Xie","orcid":"https://orcid.org/0000-0002-9588-7454","observed_orcids":["https://orcid.org/0000-0002-9588-7454","https://orcid.org/0009-0004-0629-7260"]},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie, Qianqian","raw_affiliation_strings":["Center for the Study of Language and Information , Wuhan University","School of Artifical Intelligence , Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for the Study of Language and Information , Wuhan University","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Artifical Intelligence , Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077976343","display_name":"Sophia Ananiadou","orcid":"https://orcid.org/0000-0002-4097-9191","observed_orcids":["https://orcid.org/0000-0002-4097-9191"]},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ananiadou, Sophia","raw_affiliation_strings":["Computer Science , University of Manchester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science , University of Manchester","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7124000191688538,"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/T10028","display_name":"Topic Modeling","score":0.7124000191688538,"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":0.029100000858306885,"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/T12378","display_name":"Accounting Education and Careers","score":0.023800000548362732,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8339999914169312},{"id":"https://openalex.org/keywords/cognitive-diagnosis","display_name":"cognitive diagnosis","score":0.8700000047683716},{"id":"https://openalex.org/keywords/cpa-examination","display_name":"CPA exam","score":0.6169999837875366},{"id":"https://openalex.org/keywords/knowledge-gaps","display_name":"knowledge gaps","score":0.5860000252723694},{"id":"https://openalex.org/keywords/interpretable-evaluation","display_name":"interpretable evaluation","score":0.5009999871253967}],"concepts":[{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.49630001187324524},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.48739999532699585},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.4869000017642975},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.4609000086784363},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4449000060558319},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4383000135421753},{"id":"https://openalex.org/C139043278","wikidata":"https://www.wikidata.org/wiki/Q837171","display_name":"Financial services","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C19244329","wikidata":"https://www.wikidata.org/wiki/Q208697","display_name":"Financial market","level":2,"score":0.36239999532699585},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.34439998865127563},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3425999879837036},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3098999857902527},{"id":"https://openalex.org/C23925645","wikidata":"https://www.wikidata.org/wiki/Q5449731","display_name":"Financial modeling","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C2777083192","wikidata":"https://www.wikidata.org/wiki/Q1814648","display_name":"Plain language","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C46304622","wikidata":"https://www.wikidata.org/wiki/Q374814","display_name":"Certification","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27250000834465027},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.2702000141143799},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.27000001072883606},{"id":"https://openalex.org/C109574028","wikidata":"https://www.wikidata.org/wiki/Q647525","display_name":"Behavioral economics","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2508.13491","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.13491","pdf_url":"https://arxiv.org/pdf/2508.13491","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2508.13491","doi":"https://doi.org/10.48550/arxiv.2508.13491","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.13491","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.13491","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.13491","pdf_url":"https://arxiv.org/pdf/2508.13491","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414991998.pdf","grobid_xml":"https://content.openalex.org/works/W4414991998.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W3174986053","https://openalex.org/W3198243861","https://openalex.org/W4281656839","https://openalex.org/W4285137661","https://openalex.org/W4307310886","https://openalex.org/W4320003957","https://openalex.org/W4321649220","https://openalex.org/W4322718191","https://openalex.org/W4327810158","https://openalex.org/W4385573185","https://openalex.org/W4386908207","https://openalex.org/W4388926382","https://openalex.org/W4389157038","https://openalex.org/W4390690464","https://openalex.org/W4390722666","https://openalex.org/W4390961266","https://openalex.org/W4392679398","https://openalex.org/W4399836596","https://openalex.org/W4399836748","https://openalex.org/W4399837985","https://openalex.org/W4401660192","https://openalex.org/W4402670293","https://openalex.org/W4402671960","https://openalex.org/W4403786869","https://openalex.org/W4404260035","https://openalex.org/W4405903187","https://openalex.org/W4407012932","https://openalex.org/W4411119522","https://openalex.org/W4411120358","https://openalex.org/W4412886800","https://openalex.org/W4414858196","https://openalex.org/W4414939355","https://openalex.org/W4415036142","https://openalex.org/W4415061565","https://openalex.org/W4415070727","https://openalex.org/W4415133505","https://openalex.org/W4415133727","https://openalex.org/W4416034309","https://openalex.org/W4416036914","https://openalex.org/W4416043363","https://openalex.org/W4416233039","https://openalex.org/W6910773300","https://openalex.org/W7104392137","https://openalex.org/W7131776210","https://openalex.org/W7166883127"],"related_works":["https://openalex.org/W4416080030","https://openalex.org/W7084027548","https://openalex.org/W7080307725","https://openalex.org/W7161566057","https://openalex.org/W6910010979","https://openalex.org/W4386081064","https://openalex.org/W4400374373","https://openalex.org/W6891859504","https://openalex.org/W7171735695","https://openalex.org/W7131863628"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4,107],"shown":[5],"promise":[6],"for":[7,13,71,88,213],"financial":[8,65,89,102,131,149,214],"applications,":[9],"yet":[10],"their":[11,50,112],"suitability":[12],"this":[14],"high-stakes":[15],"domain":[16,156],"remains":[17],"largely":[18],"unproven":[19],"due":[20],"to":[21,240],"inadequacies":[22],"in":[23],"existing":[24],"benchmarks.":[25],"Existing":[26],"benchmarks":[27],"solely":[28],"rely":[29,55],"on":[30,56,111,175],"score-level":[31],"evaluation,":[32],"summarizing":[33],"performance":[34],"with":[35,142,164],"a":[36,61,120,210],"single":[37,121],"score":[38],"that":[39,58,183,222],"obscures":[40],"the":[41,81,92,97,127,136],"nuanced":[42],"understanding":[43],"of":[44,64,94,145],"what":[45,101],"models":[46],"truly":[47],"know":[48],"and":[49,104,148,161,168,179,195,202,226,230,233],"precise":[51],"limitations.":[52],"They":[53],"also":[54],"datasets":[57,232],"cover":[59],"only":[60],"narrow":[62],"subset":[63],"concepts,":[66],"while":[67],"overlooking":[68],"other":[69],"essentials":[70],"real-world":[72,146],"applications.":[73],"To":[74],"address":[75],"these":[76],"gaps,":[77,188],"we":[78],"introduce":[79],"FinCDM,":[80],"first":[82,128],"cognitive":[83],"diagnosis":[84,221],"evaluation":[85,93,132,216,234],"framework":[86],"tailored":[87],"LLMs,":[90],"enabling":[91,218],"LLMs":[95,181],"at":[96],"knowledge-skill":[98],"level,":[99],"identifying":[100],"skills":[103],"knowledge":[105,170,187],"they":[106],"or":[108],"lack":[109],"based":[110],"response":[113],"patterns":[114],"across":[115],"skill-tagged":[116],"tasks,":[117],"rather":[118],"than":[119],"aggregated":[122],"number.":[123],"We":[124],"construct":[125],"CPA-KQA,":[126],"cognitively":[129],"informed":[130],"dataset":[133],"derived":[134],"from":[135],"Certified":[137],"Public":[138],"Accountant":[139],"(CPA)":[140],"examination,":[141],"comprehensive":[143],"coverage":[144],"accounting":[147],"skills.":[150],"It":[151],"is":[152],"rigorously":[153],"annotated":[154],"by":[155,199,217],"experts,":[157],"who":[158],"author,":[159],"validate,":[160],"annotate":[162],"questions":[163],"high":[165],"inter-annotator":[166],"agreement":[167],"fine-grained":[169],"labels.":[171],"Our":[172],"extensive":[173],"experiments":[174],"30":[176],"proprietary,":[177],"open-source,":[178],"domain-specific":[180],"show":[182],"FinCDM":[184,208],"reveals":[185],"hidden":[186],"identifies":[189],"under-tested":[190],"areas":[191],"such":[192],"as":[193],"tax":[194],"regulatory":[196],"reasoning":[197],"overlooked":[198],"traditional":[200],"benchmarks,":[201],"uncovers":[203],"behavioral":[204],"clusters":[205],"among":[206],"models.":[207],"introduces":[209],"new":[211],"paradigm":[212],"LLM":[215],"interpretable,":[219],"skill-aware":[220],"supports":[223],"more":[224],"trustworthy":[225],"targeted":[227],"model":[228],"development,":[229],"all":[231],"scripts":[235],"will":[236],"be":[237],"publicly":[238],"released":[239],"support":[241],"further":[242],"research.":[243]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-09T00:00:00"}