{"id":"https://openalex.org/W7161950410","doi":"https://doi.org/10.48550/arxiv.2605.20197","title":"MedicalBench: Evaluating Large Language Models Toward Improved Medical Concept Extraction","display_name":"MedicalBench: Evaluating Large Language Models Toward Improved Medical Concept Extraction","publication_year":2026,"publication_date":"2026-04-05","ids":{"openalex":"https://openalex.org/W7161950410","doi":"https://doi.org/10.48550/arxiv.2605.20197"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.20197","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20197","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.20197","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136645589","display_name":"Zhichao Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Zhichao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136617641","display_name":"Gregory D. Lyng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lyng, Gregory D.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042529162","display_name":"Sanjit Singh Batra","orcid":"https://orcid.org/0000-0001-9849-865X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Batra, Sanjit Singh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5037895048","display_name":"Robert E. Tillman","orcid":"https://orcid.org/0000-0002-6586-119X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tillman, Robert E.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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":0.6068000197410583,"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":0.6068000197410583,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.1712000072002411,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.09179999679327011,"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/unified-medical-language-system","display_name":"Unified Medical Language System","score":0.6309000253677368},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6205999851226807},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5759999752044678},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5444999933242798},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4244000017642975},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3849000036716461},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.3828999996185303},{"id":"https://openalex.org/keywords/triage","display_name":"Triage","score":0.37860000133514404},{"id":"https://openalex.org/keywords/medical-diagnosis","display_name":"Medical diagnosis","score":0.3540000021457672}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7415000200271606},{"id":"https://openalex.org/C69505689","wikidata":"https://www.wikidata.org/wiki/Q455338","display_name":"Unified Medical Language System","level":2,"score":0.6309000253677368},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6205999851226807},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5759999752044678},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5444999933242798},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5297999978065491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5209000110626221},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.47589999437332153},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4244000017642975},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3849000036716461},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3828999996185303},{"id":"https://openalex.org/C2777120189","wikidata":"https://www.wikidata.org/wiki/Q780067","display_name":"Triage","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35519999265670776},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3431999981403351},{"id":"https://openalex.org/C166151441","wikidata":"https://www.wikidata.org/wiki/Q4923601","display_name":"Causation","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C2779231881","wikidata":"https://www.wikidata.org/wiki/Q5977147","display_name":"Medical literature","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C28076734","wikidata":"https://www.wikidata.org/wiki/Q63087","display_name":"Coreference","level":3,"score":0.2913999855518341},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C2776289891","wikidata":"https://www.wikidata.org/wiki/Q1931511","display_name":"Neglect","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C167729594","wikidata":"https://www.wikidata.org/wiki/Q17736","display_name":"Axiom","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C145642194","wikidata":"https://www.wikidata.org/wiki/Q870895","display_name":"Health informatics","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.20197","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20197","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.20197","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20197","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4637523591518402,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Medical":[0],"concept":[1,63,76,146,207],"extraction":[2,64,77,147],"from":[3,92],"electronic":[4],"health":[5],"records":[6],"underpins":[7],"many":[8],"downstream":[9],"applications,":[10],"yet":[11],"remains":[12,166],"challenging":[13],"because":[14],"medically":[15,221,232],"meaningful":[16],"concepts":[17,40,51,223],"are":[18],"frequently":[19],"implied":[20],"rather":[21,193],"than":[22,194],"explicitly":[23,49],"stated":[24,50],"in":[25,41,228],"medical":[26,42,62,71,75,83,115,135,145,206,214],"narratives.":[27],"Existing":[28],"benchmarks":[29],"with":[30,65,87,134],"human-annotated":[31],"evidence":[32,66,89,151],"spans":[33],"underscore":[34],"the":[35,100,169,199],"importance":[36],"of":[37,53,155,171],"grounding":[38,67],"extracted":[39],"text.":[43],"However,":[44],"they":[45],"predominantly":[46],"focus":[47],"on":[48],"instead":[52],"implicit":[54,70,123],"concepts.":[55,175],"We":[56,138,176],"present":[57],"MedicalBench,":[58],"a":[59,79,105,210,229],"benchmark":[60,202],"for":[61,203,212],"that":[68,164,179,188,217],"evaluates":[69],"reasoning.":[72],"MedicalBench":[73,189,197],"formulates":[74],"as":[78],"verification":[80],"task":[81],"over":[82],"note-concept":[84],"pairs,":[85],"coupled":[86],"sentence-level":[88,150],"identification.":[90],"Built":[91],"MIMIC-IV":[93],"discharge":[94],"summaries":[95],"and":[96,117,128,148,158,224,231],"human-verified":[97],"ICD-10":[98],"codes,":[99],"dataset":[101],"is":[102,181],"curated":[103],"through":[104],"multi-stage":[106],"large":[107],"language":[108,215],"model":[109],"(LLM)":[110],"triage":[111],"pipeline":[112],"followed":[113],"by":[114],"annotation":[116],"expert":[118,136],"review.":[119],"It":[120],"deliberately":[121],"includes":[122],"positives,":[124],"semantically":[125],"confusable":[126],"negatives,":[127],"cases":[129],"where":[130],"LLM":[131],"judgments":[132],"disagree":[133],"assessments.":[137],"define":[139],"two":[140],"complementary":[141],"evaluation":[142],"tasks:":[143],"(1)":[144],"(2)":[149],"retrieval,":[152],"enabling":[153],"assessment":[154],"both":[156,219],"correctness":[157],"interpretability.":[159],"Benchmarking":[160],"state-of-the-art":[161],"LLMs":[162],"reveals":[163],"performance":[165,180],"modest,":[167],"highlighting":[168],"difficulty":[170,192],"extracting":[172],"implicitly":[173],"expressed":[174],"further":[177],"show":[178],"largely":[182],"invariant":[183],"to":[184],"note":[185],"length,":[186],"indicating":[187],"isolates":[190],"reasoning":[191],"superficial":[195],"confounders.":[196],"provides":[198],"first":[200],"systematic":[201],"implicit,":[204],"evidence-grounded":[205],"extraction,":[208],"offering":[209],"foundation":[211],"developing":[213],"models":[216],"can":[218],"identify":[220],"relevant":[222],"justify":[225],"their":[226],"predictions":[227],"transparent":[230],"faithful":[233],"manner.":[234]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-22T00:00:00"}