{"id":"https://openalex.org/W7202273176","doi":"https://doi.org/10.48550/arxiv.2608.11047","title":"V-FiLLM: Verified Financial LLM Reasoning Benchmark","display_name":"V-FiLLM: Verified Financial LLM Reasoning Benchmark","publication_year":2026,"publication_date":"2026-08-11","ids":{"openalex":"https://openalex.org/W7202273176","doi":"https://doi.org/10.48550/arxiv.2608.11047"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.11047","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.11047","pdf_url":"https://arxiv.org/pdf/2608.11047","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/2608.11047","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5146959555","display_name":"Alicia Larsen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Larsen, Alicia","raw_affiliation_strings":["ETH Z\u00fcrich , Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich , Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033995734","display_name":"Victoire Laurent","orcid":"https://orcid.org/0000-0002-1060-9640","observed_orcids":["https://orcid.org/0000-0002-1060-9640"]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Laurent, Victoire","raw_affiliation_strings":["ETH Z\u00fcrich , Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich , Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148126882","display_name":"Aulia Kharis Rakhmasari","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Rakhmasari, Aulia Kharis","raw_affiliation_strings":["ETH Z\u00fcrich , Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich , Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147045362","display_name":"Lara Turgut","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Turgut, Lara","raw_affiliation_strings":["ETH Z\u00fcrich , Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich , Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057217842","display_name":"Nino Antulov-Fantulin","orcid":"https://orcid.org/0000-0002-4337-2475","observed_orcids":["https://orcid.org/0000-0002-4337-2475"]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Antulov-Fantulin, Nino","raw_affiliation_strings":["Aisot Technologies Ltd","ETH Z\u00fcrich , Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aisot Technologies Ltd","institution_ids":[]},{"raw_affiliation_string":"ETH Z\u00fcrich , Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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":0.8511000275611877,"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":0.8511000275611877,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.03009999915957451,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.025599999353289604,"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/financial-reasoning","display_name":"financial reasoning","score":0.8730000257492065},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7160000205039978},{"id":"https://openalex.org/keywords/benchmark-generation","display_name":"benchmark generation","score":0.902999997138977},{"id":"https://openalex.org/keywords/computation-trees","display_name":"computation trees","score":0.7689999938011169},{"id":"https://openalex.org/keywords/structured-data","display_name":"structured data","score":0.4339999854564667},{"id":"https://openalex.org/keywords/financial-question-answering","display_name":"financial question answering","score":0.6150000095367432},{"id":"https://openalex.org/keywords/low-rank-adaptation","display_name":"low-rank adaptation","score":0.7319999933242798},{"id":"https://openalex.org/keywords/chain-of-thought","display_name":"chain-of-thought","score":0.7730000019073486},{"id":"https://openalex.org/keywords/compositional-reasoning","display_name":"compositional reasoning","score":0.8960000276565552}],"concepts":[{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.6718000173568726},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6452000141143799},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6323999762535095},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6122000217437744},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5325000286102295},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.48840001225471497},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.4683000147342682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4668000042438507},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4530999958515167},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.4521999955177307},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.41359999775886536},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.4050000011920929},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.38420000672340393},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3562000095844269},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.11047","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.11047","pdf_url":"https://arxiv.org/pdf/2608.11047","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.11047","doi":"https://doi.org/10.48550/arxiv.2608.11047","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.11047","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.11047","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.11047","pdf_url":"https://arxiv.org/pdf/2608.11047","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7202273176.pdf","grobid_xml":"https://content.openalex.org/works/W7202273176.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2913946806","https://openalex.org/W2951365061","https://openalex.org/W2971822538","https://openalex.org/W3168867926","https://openalex.org/W3174986053","https://openalex.org/W3198243861","https://openalex.org/W4281483047","https://openalex.org/W4281656839","https://openalex.org/W4361230739","https://openalex.org/W4385573185","https://openalex.org/W4387294159","https://openalex.org/W4387559386","https://openalex.org/W4388926373","https://openalex.org/W4388926382","https://openalex.org/W4402671590","https://openalex.org/W4403324134","https://openalex.org/W7083832184","https://openalex.org/W7133191918"],"related_works":["https://openalex.org/W4388684812","https://openalex.org/W7138161862","https://openalex.org/W7172310579","https://openalex.org/W4412888535","https://openalex.org/W7201963949","https://openalex.org/W4414632912","https://openalex.org/W7204846388","https://openalex.org/W7123597229","https://openalex.org/W4405907414","https://openalex.org/W4411271241"],"abstract_inverted_index":{"While":[0],"existing":[1],"benchmarks":[2,31],"have":[3],"made":[4],"substantial":[5],"progress":[6],"in":[7,37,134,187],"evaluating":[8,106],"LLMs":[9],"across":[10],"STEM":[11],"domains,":[12],"financial":[13,29,99,136,188],"reasoning":[14,30,119,137,186],"over":[15,138],"structured":[16],"data":[17],"remains":[18],"comparatively":[19],"less":[20],"explored.":[21],"We":[22,140],"introduce":[23],"V-FiLLM,":[24],"a":[25,82,181],"framework":[26],"that":[27,112,143,176],"generates":[28],"from":[32,64,153],"executable":[33],"computation":[34,95],"trees":[35],"grounded":[36],"real":[38],"tables,":[39],"yielding":[40],"items":[41,69],"whose":[42],"answers":[43],"are":[44,49],"correct":[45],"by":[46,165],"construction.":[47],"Trees":[48],"evaluated":[50],"symbolically":[51],"to":[52,116,124,155],"obtain":[53],"ground":[54],"truth":[55],"and":[56,79,102,122,160],"rendered":[57],"into":[58],"natural-language":[59],"questions,":[60],"removing":[61],"any":[62],"model":[63,164],"the":[65,162],"labeling":[66],"loop,":[67],"so":[68],"can":[70],"be":[71],"generated":[72],"at":[73],"arbitrary":[74],"scale":[75],"without":[76,80],"annotation":[77],"cost":[78],"inheriting":[81],"generator's":[83],"error":[84],"rate.":[85],"V-FiLLM":[86],"exposes":[87],"four":[88],"independently":[89],"controllable":[90],"axes":[91],"of":[92],"difficulty":[93],"including":[94],"depth,":[96],"expression":[97],"breadth,":[98],"concept":[100],"complexity,":[101],"context":[103],"size.":[104],"By":[105],"on":[107,147,157,168],"open-source":[108],"models,":[109],"we":[110],"find":[111],"accuracy":[113,152],"falls":[114],"up":[115,123],"51%":[117],"as":[118],"depth":[120],"increases,":[121],"47%":[125],"points":[126,167],"under":[127],"adversarial":[128],"numerical":[129],"perturbations,":[130],"highlighting":[131],"remaining":[132],"challenges":[133],"robust":[135],"tables.":[139],"further":[141],"show":[142],"lightweight":[144],"LoRA":[145],"fine-tuning":[146],"verified":[148],"chain-of-thought":[149],"traces":[150],"improves":[151],"81.1%":[154],"85.6%":[156],"held-out":[158],"problems":[159],"outperforms":[161],"base":[163],"5%":[166],"FinQA":[169],"(Chen":[170],"et":[171],"al.,":[172],"2022a),":[173],"s),":[174],"suggesting":[175],"targeted,":[177],"low-cost":[178],"adaptation":[179],"is":[180],"promising":[182],"direction":[183],"for":[184],"compositional":[185],"QA.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-13T00:00:00"}