{"id":"https://openalex.org/W7140080743","doi":"https://doi.org/10.18653/v1/2026.eacl-demo.33","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":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140080743","doi":"https://doi.org/10.18653/v1/2026.eacl-demo.33"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.eacl-demo.33","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-demo.33","pdf_url":"https://aclanthology.org/2026.eacl-demo.33.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":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.eacl-demo.33.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5146908278","display_name":"Adam Dejl","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Adam Dejl","raw_affiliation_strings":["Imperial College London Department of Computing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London Department of Computing","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5146640617","display_name":"Jonathan Pearson","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129883","display_name":"NHS Digital","ror":"https://ror.org/03am1eg44","country_code":"GB","type":"government","lineage":["https://openalex.org/I4210129883"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jonathan Pearson","raw_affiliation_strings":["NHS England Transformation Directorate"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NHS England Transformation Directorate","institution_ids":["https://openalex.org/I4210129883"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.23563543,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"480","last_page":"491"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.14249999821186066,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.14249999821186066,"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":0.08649999648332596,"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":0.06989999860525131,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.2815999984741211},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.259799987077713},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.2583000063896179},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.2443999946117401},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2354000061750412}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3961000144481659},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2443999946117401},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2354000061750412},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2345999926328659},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.23360000550746918},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.22050000727176666},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.21739999949932098}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2026.eacl-demo.33","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-demo.33","pdf_url":"https://aclanthology.org/2026.eacl-demo.33.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":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2602.18823","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.18823","pdf_url":"https://arxiv.org/pdf/2602.18823","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,"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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-demo.33","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-demo.33","pdf_url":"https://aclanthology.org/2026.eacl-demo.33.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":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140080743.pdf","grobid_xml":"https://content.openalex.org/works/W7140080743.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Robust":[0],"and":[1,17,61,71,99,102,107,132,174,181],"comprehensive":[2],"evaluation":[3,43,62,66,85,100,110,129,143],"of":[4,96,141,151,160],"large":[5],"language":[6],"models":[7],"(LLMs)":[8],"is":[9,116],"essential":[10],"for":[11,82,87,92,112],"identifying":[12],"effective":[13],"LLM":[14],"system":[15],"configurations":[16],"mitigating":[18],"risks":[19],"associated":[20,176],"with":[21,177],"deploying":[22,108],"LLMs":[23],"in":[24,105,128,153],"sensitive":[25],"domains.However,":[26],"traditional":[27],"statistical":[28],"metrics":[29],"are":[30,179],"poorly":[31],"suited":[32],"to":[33,38,69],"open-ended":[34],"generation":[35,159],"tasks,":[36],"leading":[37],"growing":[39],"reliance":[40],"on":[41,55],"LLM-based":[42],"methods.These":[44],"methods,":[45],"while":[46],"often":[47],"more":[48],"flexible,":[49,79],"introduce":[50],"additional":[51],"complexity:":[52],"they":[53],"depend":[54],"carefully":[56],"chosen":[57],"models,":[58],"prompts,":[59],"parameters,":[60],"strategies,":[63,101],"making":[64],"the":[65,139,149,158],"process":[67],"prone":[68],"misconfiguration":[70],"bias.In":[72],"this":[73],"work,":[74],"we":[75],"present":[76],"EvalSense,":[77],"a":[78,93,154,168],"extensible":[80],"framework":[81],"constructing":[83],"domainspecific":[84],"suites":[86],"LLMs.EvalSense":[88],"provides":[89],"out-of-the-box":[90],"support":[91],"broad":[94],"range":[95],"model":[97],"providers":[98],"assists":[103],"users":[104,127],"selecting":[106],"suitable":[109],"methods":[111],"their":[113],"specific":[114],"use-cases.This":[115],"achieved":[117],"through":[118],"two":[119],"unique":[120],"components:":[121],"(1)":[122],"an":[123],"interactive":[124],"guide":[125],"aiding":[126],"method":[130],"selection":[131],"(2)":[133],"automated":[134],"meta-evaluation":[135],"tools":[136],"that":[137],"assess":[138],"reliability":[140],"different":[142],"approaches":[144],"using":[145,167],"perturbed":[146],"data.We":[147],"demonstrate":[148],"effectiveness":[150],"EvalSense":[152,178],"case":[155],"study":[156],"involving":[157],"clinical":[161],"notes":[162],"from":[163],"unstructured":[164],"doctor-patient":[165],"dialogues,":[166],"popular":[169],"open":[170],"dataset.All":[171],"code,":[172],"documentation,":[173],"assets":[175],"open-source":[180],"publicly":[182],"available":[183],"at":[184],"https:":[185],"//github.com/nhsengland/evalsense.":[186]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2026-03-01T00:00:00"}