{"id":"https://openalex.org/W4412888535","doi":"https://doi.org/10.18653/v1/2025.findings-acl.457","title":"XFinBench: Benchmarking LLMs in Complex Financial Problem Solving and Reasoning","display_name":"XFinBench: Benchmarking LLMs in Complex Financial Problem Solving and Reasoning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888535","doi":"https://doi.org/10.18653/v1/2025.findings-acl.457"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.457","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.457","pdf_url":"https://aclanthology.org/2025.findings-acl.457.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 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.457.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101798381","display_name":"Zhihan Zhang","orcid":"https://orcid.org/0000-0003-0231-5033"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhihan Zhang","raw_affiliation_strings":["School of Computing and Information Systems , Singapore Management University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems , Singapore Management University ,","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013247988","display_name":"Yixin Cao","orcid":"https://orcid.org/0000-0002-6927-438X"},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixin Cao","raw_affiliation_strings":["Institute of Trustworthy Embodied AI , Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI , Fudan University","institution_ids":["https://openalex.org/I4210139618"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081165986","display_name":"Lizi Liao","orcid":"https://orcid.org/0000-0002-9973-3305"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lizi Liao","raw_affiliation_strings":["School of Computing and Information Systems , Singapore Management University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems , Singapore Management University ,","institution_ids":["https://openalex.org/I79891267"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.0712,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.97182368,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"8715","last_page":"8758"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13794","display_name":"Financial Reporting and XBRL","score":0.9563000202178955,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13794","display_name":"Financial Reporting and XBRL","score":0.9563000202178955,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"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/benchmarking","display_name":"Benchmarking","score":0.8300294876098633},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.44128337502479553},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.431287556886673},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.23872125148773193},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1982714831829071},{"id":"https://openalex.org/keywords/management","display_name":"Management","score":0.1460731029510498}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8300294876098633},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.44128337502479553},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.431287556886673},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.23872125148773193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1982714831829071},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.1460731029510498}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.457","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.457","pdf_url":"https://aclanthology.org/2025.findings-acl.457.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 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-11790","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/10788","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.18653/v1/2025.findings-acl.457","raw_type":"Conference Proceeding Article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.457","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.457","pdf_url":"https://aclanthology.org/2025.findings-acl.457.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 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2342870495","display_name":null,"funder_award_id":"AcRF\u2010Tier2","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"},{"id":"https://openalex.org/G6854926366","display_name":null,"funder_award_id":"Tier 2","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"}],"funders":[{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888535.pdf","grobid_xml":"https://content.openalex.org/works/W4412888535.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699"],"abstract_inverted_index":{"Solving":[0],"financial":[1],"problems":[2,41],"demands":[3],"complex":[4],"reasoning,":[5,62],"multimodal":[6],"data":[7],"processing,":[8],"and":[9,67,107,124,150,154,172],"a":[10,25,113],"broad":[11],"technical":[12],"understanding,":[13,60],"presenting":[14],"unique":[15],"challenges":[16],"for":[17,120],"current":[18],"large":[19],"language":[20],"models":[21],"(LLMs).We":[22],"introduce":[23],"XFINBENCH,":[24,57,70],"novel":[26],"benchmark":[27],"with":[28,47,88,101,116],"4,235":[29],"examples":[30],"designed":[31],"to":[32,129,137,152,166],"evaluate":[33],"LLM's":[34],"ability":[35],"in":[36,104,158,170],"solving":[37],"compleX,":[38],"knowledge-intensive":[39],"Financial":[40],"across":[42],"diverse":[43],"graduate-level":[44],"finance":[45,118],"topics":[46],"multi-modal":[48],"context.We":[49],"identify":[50],"five":[51],"core":[52],"capabilities":[53],"of":[54,92,156],"LLMs":[55],"using":[56],"i.e,":[58],"terminology":[59],"temporal":[61,105],"future":[63],"forecasting,":[64],"scenario":[65,108],"planning,":[66],"numerical":[68],"modelling.Upon":[69],"we":[71],"conduct":[72],"extensive":[73],"experiments":[74],"on":[75],"18":[76],"leading":[77,165],"models.The":[78],"result":[79],"shows":[80],"that":[81,126,145],"o1":[82],"is":[83],"the":[84,130,159],"best-performing":[85],"text-only":[86],"model":[87],"an":[89],"overall":[90],"accuracy":[91,135],"67.3%,":[93],"but":[94],"still":[95],"lags":[96],"significantly":[97],"behind":[98],"human":[99],"experts":[100],"12.5%,":[102],"especially":[103],"reasoning":[106],"planning":[109],"capabilities.We":[110],"further":[111],"construct":[112],"knowledge":[114,121,128],"bank":[115],"3,032":[117],"terms":[119],"augmentation":[122],"analysis,":[123],"find":[125],"relevant":[127],"question":[131],"only":[132],"brings":[133],"consistent":[134],"improvements":[136],"small":[138],"opensource":[139],"model.Additionally,":[140],"our":[141],"error":[142],"analysis":[143],"reveals":[144],"rounding":[146],"errors":[147],"during":[148],"calculation":[149],"blindness":[151],"position":[153],"intersection":[155],"curves":[157],"image":[160],"are":[161],"two":[162],"primary":[163],"issues":[164],"model's":[167],"poor":[168],"performance":[169],"calculating":[171],"visual-context":[173],"questions,":[174],"respectively.1":[175]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-25T07:29:55.448023","created_date":"2025-10-10T00:00:00"}
