{"id":"https://openalex.org/W7166840400","doi":"https://doi.org/10.18653/v1/2026.findings-acl.901","title":"How Robust Are Large Language Models for Clinical Numeracy? An Empirical Study on Numerical Reasoning Abilities in Clinical Contexts","display_name":"How Robust Are Large Language Models for Clinical Numeracy? An Empirical Study on Numerical Reasoning Abilities in Clinical Contexts","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166840400","doi":"https://doi.org/10.18653/v1/2026.findings-acl.901"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.901","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.901","pdf_url":"https://aclanthology.org/2026.findings-acl.901.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.901.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104021102","display_name":"Minh-Vuong Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minh-Vuong Nguyen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006717459","display_name":"Fatemeh Shiri","orcid":"https://orcid.org/0000-0001-8752-2132"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fatemeh Shiri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139811684","display_name":"Zhuang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuang Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133553937","display_name":"Karin Verspoor","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karin Verspoor","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":0.90178571,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18113","last_page":"18129"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12574","display_name":"Clinical Reasoning and Diagnostic Skills","score":0.19869999587535858,"subfield":{"id":"https://openalex.org/subfields/2714","display_name":"Family Practice"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T12574","display_name":"Clinical Reasoning and Diagnostic Skills","score":0.19869999587535858,"subfield":{"id":"https://openalex.org/subfields/2714","display_name":"Family Practice"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.1599999964237213,"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/T10028","display_name":"Topic Modeling","score":0.1160999983549118,"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/empirical-research","display_name":"Empirical research","score":0.583299994468689},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.3440999984741211},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3431999981403351},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.3240000009536743},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.2946000099182129},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.28200000524520874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5906999707221985},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.583299994468689},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5116999745368958},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40529999136924744},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3555999994277954},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3434999883174896},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3037000000476837},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C133199616","wikidata":"https://www.wikidata.org/wiki/Q25386885","display_name":"Empirical modelling","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.27070000767707825},{"id":"https://openalex.org/C2779313563","wikidata":"https://www.wikidata.org/wiki/Q17072565","display_name":"On Language","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2590999901294708},{"id":"https://openalex.org/C2986605239","wikidata":"https://www.wikidata.org/wiki/Q925667","display_name":"Numerical models","level":3,"score":0.25769999623298645},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.901","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.901","pdf_url":"https://aclanthology.org/2026.findings-acl.901.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.901","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.901","pdf_url":"https://aclanthology.org/2026.findings-acl.901.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/4","score":0.865334153175354,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166840400.pdf","grobid_xml":"https://content.openalex.org/works/W7166840400.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"are":[4],"increasingly":[5],"being":[6],"explored":[7],"for":[8,32,172],"clinical":[9,27,33,54,74],"question":[10,113],"answering":[11],"and":[12,45,82,108,134,157],"decision":[13],"support,":[14],"yet":[15],"safe":[16],"deployment":[17],"critically":[18],"requires":[19],"reliable":[20,174],"handling":[21],"of":[22,30,50,61,73],"patient":[23],"measurements":[24],"in":[25,92],"heterogeneous":[26],"notes.Existing":[28],"evaluations":[29],"LLMs":[31,117],"numerical":[34,51,175],"reasoning":[35,176],"provide":[36],"limited":[37],"operation-level":[38],"coverage,":[39],"restricted":[40],"primarily":[41],"to":[42,151,166],"arithmetic":[43,78],"computation,":[44,79],"rarely":[46],"assess":[47],"the":[48,104],"robustness":[49],"understanding":[52],"across":[53],"note":[55],"formats.We":[56],"introduce":[57],"ClinicNumRobBench,":[58],"a":[59,98,169],"benchmark":[60],"1,624":[62],"context-question":[63],"instances":[64],"with":[65,125,138],"ground-truth":[66],"answers":[67],"that":[68,119],"evaluates":[69],"four":[70],"main":[71],"types":[72],"numeracy:":[75],"value":[76,120],"retrieval,":[77],"relational":[80,132],"comparison,":[81],"aggregation.To":[83],"stress-test":[84],"robustness,":[85],"ClinicNumRob-Bench":[86],"presents":[87],"longitudinal":[88],"MIMIC-IV":[89],"vitalsign":[90],"records":[91],"three":[93],"semantically":[94],"equivalent":[95],"representations,":[96],"including":[97],"real-world":[99],"notestyle":[100],"variant":[101],"derived":[102],"from":[103],"Open":[105],"Patients":[106],"dataset,":[107],"instantiates":[109],"queries":[110],"using":[111],"42":[112],"templates.Experiments":[114],"on":[115,144],"17":[116],"show":[118],"retrieval":[121],"is":[122],"generally":[123],"strong,":[124],"most":[126],"models":[127,140,153],"exceeding":[128],"85%":[129],"accuracy,":[130],"while":[131],"comparison":[133],"aggregation":[135],"remain":[136],"challenging,":[137],"some":[139],"scoring":[141],"below":[142],"15%.Fine-tuning":[143],"medical":[145],"data":[146],"can":[147],"reduce":[148],"numeracy":[149],"relative":[150],"base":[152],"by":[154],"over":[155],"30%,":[156],"performance":[158],"drops":[159],"under":[160],"note-style":[161],"variation":[162],"indicate":[163],"LLM":[164],"sensitivity":[165],"format.Clinic-NumRobBench":[167],"offers":[168],"rigorous":[170],"testbed":[171],"clinically":[173],"1":[177],".":[178]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}