{"id":"https://openalex.org/W7131400266","doi":"https://doi.org/10.48550/arxiv.2602.18823","title":"EvalSense: A Framework for Domain-Specific LLM (Meta-)Evaluation","display_name":"EvalSense: A Framework for Domain-Specific LLM (Meta-)Evaluation","publication_year":2026,"publication_date":"2026-02-21","ids":{"openalex":"https://openalex.org/W7131400266","doi":"https://doi.org/10.48550/arxiv.2602.18823"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.18823","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.18823","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":null,"license_id":null,"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.2602.18823","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126789347","display_name":"Adam Dejl","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dejl, Adam","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126819369","display_name":"Jonathan Pearson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pearson, Jonathan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5126789347"],"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.36010000109672546,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.36010000109672546,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"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/T10028","display_name":"Topic Modeling","score":0.24469999969005585,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.1264999955892563,"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/process","display_name":"Process (computing)","score":0.6320000290870667},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5478000044822693},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4927000105381012},{"id":"https://openalex.org/keywords/evaluation-methods","display_name":"Evaluation methods","score":0.4440000057220459},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3610999882221222},{"id":"https://openalex.org/keywords/extensibility","display_name":"Extensibility","score":0.3434999883174896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7376000285148621},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6320000290870667},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.6080999970436096},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5478000044822693},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4927000105381012},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.4440000057220459},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.388700008392334},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3301999866962433},{"id":"https://openalex.org/C5395021","wikidata":"https://www.wikidata.org/wiki/Q1061410","display_name":"Program evaluation","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.2921000123023987},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2854999899864197},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.25060001015663147},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.18823","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.18823","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2602.18823","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.18823","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Robust":[0],"and":[1,17,63,73,103,106,111,137,181,188],"comprehensive":[2],"evaluation":[3,44,64,68,88,104,114,134,148],"of":[4,100,146,157,166],"large":[5],"language":[6],"models":[7],"(LLMs)":[8],"is":[9,121],"essential":[10],"for":[11,85,90,96,116],"identifying":[12],"effective":[13],"LLM":[14],"system":[15],"configurations":[16],"mitigating":[18],"risks":[19],"associated":[20,183],"with":[21,184],"deploying":[22,112],"LLMs":[23],"in":[24,109,133,159],"sensitive":[25],"domains.":[26],"However,":[27],"traditional":[28],"statistical":[29],"metrics":[30],"are":[31,186],"poorly":[32],"suited":[33],"to":[34,39,71],"open-ended":[35],"generation":[36,165],"tasks,":[37],"leading":[38],"growing":[40],"reliance":[41],"on":[42,57],"LLM-based":[43],"methods.":[45],"These":[46],"methods,":[47],"while":[48],"often":[49],"more":[50],"flexible,":[51,82],"introduce":[52],"additional":[53],"complexity:":[54],"they":[55],"depend":[56],"carefully":[58],"chosen":[59],"models,":[60],"prompts,":[61],"parameters,":[62],"strategies,":[65,105],"making":[66],"the":[67,144,155,164],"process":[69],"prone":[70],"misconfiguration":[72],"bias.":[74],"In":[75],"this":[76],"work,":[77],"we":[78],"present":[79],"EvalSense,":[80],"a":[81,97,160,174],"extensible":[83],"framework":[84],"constructing":[86],"domain-specific":[87],"suites":[89],"LLMs.":[91],"EvalSense":[92,158,185],"provides":[93],"out-of-the-box":[94],"support":[95],"broad":[98],"range":[99],"model":[101],"providers":[102],"assists":[107],"users":[108,132],"selecting":[110],"suitable":[113],"methods":[115],"their":[117],"specific":[118],"use-cases.":[119],"This":[120],"achieved":[122],"through":[123],"two":[124],"unique":[125],"components:":[126],"(1)":[127],"an":[128],"interactive":[129],"guide":[130],"aiding":[131],"method":[135],"selection":[136],"(2)":[138],"automated":[139],"meta-evaluation":[140],"tools":[141],"that":[142],"assess":[143],"reliability":[145],"different":[147],"approaches":[149],"using":[150,173],"perturbed":[151],"data.":[152],"We":[153],"demonstrate":[154],"effectiveness":[156],"case":[161],"study":[162],"involving":[163],"clinical":[167],"notes":[168],"from":[169],"unstructured":[170],"doctor-patient":[171],"dialogues,":[172],"popular":[175],"open":[176],"dataset.":[177],"All":[178],"code,":[179],"documentation,":[180],"assets":[182],"open-source":[187],"publicly":[189],"available":[190],"at":[191],"https://github.com/nhsengland/evalsense.":[192]},"counts_by_year":[],"updated_date":"2026-02-26T06:34:08.959763","created_date":"2026-02-26T00:00:00"}