{"id":"https://openalex.org/W4416382572","doi":"https://doi.org/10.62036/isd.2025.50","title":"Expert Versus Metric-Based Evaluation: Testing the Reliability of Evaluation Metrics in Large Language Models Assessment","display_name":"Expert Versus Metric-Based Evaluation: Testing the Reliability of Evaluation Metrics in Large Language Models Assessment","publication_year":2025,"publication_date":"2025-11-17","ids":{"openalex":"https://openalex.org/W4416382572","doi":"https://doi.org/10.62036/isd.2025.50"},"language":null,"primary_location":{"id":"doi:10.62036/isd.2025.50","is_oa":true,"landing_page_url":"https://doi.org/10.62036/isd.2025.50","pdf_url":"https://aisel.aisnet.org/cgi/viewcontent.cgi?article=1729&context=isd2014","source":{"id":"https://openalex.org/S4404677940","display_name":"Proceedings of the International Conference on Information Systems Development","issn_l":"2938-5202","issn":["2938-5202"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on Information Systems Development","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aisel.aisnet.org/cgi/viewcontent.cgi?article=1729&context=isd2014","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107083462","display_name":"Bart\u0142omiej Balsamski","orcid":"https://orcid.org/0009-0001-4917-1295"},"institutions":[{"id":"https://openalex.org/I23574469","display_name":"Krakow University of Economics","ror":"https://ror.org/0262te083","country_code":"PL","type":"education","lineage":["https://openalex.org/I23574469"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Bartlomiej Balsamski","raw_affiliation_strings":["Krakow University of Economics, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Krakow University of Economics, Poland","institution_ids":["https://openalex.org/I23574469"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107083463","display_name":"Jakub Kanclerz","orcid":null},"institutions":[{"id":"https://openalex.org/I23574469","display_name":"Krakow University of Economics","ror":"https://ror.org/0262te083","country_code":"PL","type":"education","lineage":["https://openalex.org/I23574469"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Jakub Kanclerz","raw_affiliation_strings":["Krakow University of Economics, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Krakow University of Economics, Poland","institution_ids":["https://openalex.org/I23574469"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090496332","display_name":"Dariusz Put","orcid":"https://orcid.org/0000-0003-3686-6749"},"institutions":[{"id":"https://openalex.org/I23574469","display_name":"Krakow University of Economics","ror":"https://ror.org/0262te083","country_code":"PL","type":"education","lineage":["https://openalex.org/I23574469"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Dariusz Put","raw_affiliation_strings":["Krakow University of Economics, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Krakow University of Economics, Poland","institution_ids":["https://openalex.org/I23574469"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044631340","display_name":"Janusz Stal","orcid":"https://orcid.org/0000-0002-0199-7848"},"institutions":[{"id":"https://openalex.org/I23574469","display_name":"Krakow University of Economics","ror":"https://ror.org/0262te083","country_code":"PL","type":"education","lineage":["https://openalex.org/I23574469"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Janusz Stal","raw_affiliation_strings":["Krakow University of Economics, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Krakow University of Economics, Poland","institution_ids":["https://openalex.org/I23574469"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I23574469"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.23430000245571136,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.23430000245571136,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.08940000087022781,"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/T13629","display_name":"Text Readability and Simplification","score":0.0828000009059906,"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/reliability","display_name":"Reliability (semiconductor)","score":0.6984000205993652},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6438999772071838},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6087999939918518},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6047999858856201},{"id":"https://openalex.org/keywords/expert-system","display_name":"Expert system","score":0.41839998960494995},{"id":"https://openalex.org/keywords/likert-scale","display_name":"Likert scale","score":0.3901999890804291}],"concepts":[{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.6984000205993652},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6438999772071838},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6376000046730042},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6087999939918518},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6047999858856201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47040000557899475},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4666999876499176},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C105776082","wikidata":"https://www.wikidata.org/wiki/Q617473","display_name":"Likert scale","level":2,"score":0.3901999890804291},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38580000400543213},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37619999051094055},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.34869998693466187},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C3018868096","wikidata":"https://www.wikidata.org/wiki/Q2693233","display_name":"Internal consistency","level":3,"score":0.30160000920295715},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.2590000033378601},{"id":"https://openalex.org/C2778883600","wikidata":"https://www.wikidata.org/wiki/Q2390977","display_name":"Language proficiency","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.62036/isd.2025.50","is_oa":true,"landing_page_url":"https://doi.org/10.62036/isd.2025.50","pdf_url":"https://aisel.aisnet.org/cgi/viewcontent.cgi?article=1729&context=isd2014","source":{"id":"https://openalex.org/S4404677940","display_name":"Proceedings of the International Conference on Information Systems Development","issn_l":"2938-5202","issn":["2938-5202"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on Information Systems Development","raw_type":"proceedings-article"},{"id":"pmh:oai:aisel.aisnet.org:isd2014-1729","is_oa":false,"landing_page_url":"https://aisel.aisnet.org/isd2014/proceedings2025/datascience/20","pdf_url":null,"source":{"id":"https://openalex.org/S30879505","display_name":"Journal of the Association for Information Systems","issn_l":"1536-9323","issn":["1536-9323"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310321080","host_organization_name":"Association for Information Systems","host_organization_lineage":["https://openalex.org/P4310321080"],"host_organization_lineage_names":["Association for Information Systems"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the International Conference on Information Systems Development (ISD)","raw_type":"text"}],"best_oa_location":{"id":"doi:10.62036/isd.2025.50","is_oa":true,"landing_page_url":"https://doi.org/10.62036/isd.2025.50","pdf_url":"https://aisel.aisnet.org/cgi/viewcontent.cgi?article=1729&context=isd2014","source":{"id":"https://openalex.org/S4404677940","display_name":"Proceedings of the International Conference on Information Systems Development","issn_l":"2938-5202","issn":["2938-5202"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on Information Systems Development","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416382572.pdf","grobid_xml":"https://content.openalex.org/works/W4416382572.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"study":[1],"examines":[2],"the":[3,19,92,97,109,116],"reliability":[4,124],"of":[5,21,26,53],"automatic":[6,79],"evaluation":[7,106],"metrics":[8,80],"in":[9,18,38,125],"assessing":[10],"responses":[11,47],"generated":[12,46],"by":[13],"large":[14],"language":[15],"models":[16],"(LLMs)":[17],"context":[20],"university":[22],"recruitment.":[23],"A":[24],"total":[25],"113":[27],"domain-specific":[28],"questions":[29],"were":[30,48,62],"used":[31],"to":[32,114],"prompt":[33],"five":[34],"prominent":[35],"LLMs,":[36],"each":[37],"three":[39,51],"configurations:":[40],"basic,":[41],"document-context,":[42],"and":[43,57,100],"internet-context.":[44],"The":[45,74],"evaluated":[49],"using":[50,69],"categories":[52],"metrics:":[54],"lexical,":[55],"semantic,":[56],"LLM-asa-Judge.":[58],"These":[59],"metric-based":[60],"assessments":[61],"subsequently":[63],"compared":[64],"with":[65,86,119],"expert":[66,87,120],"evaluations":[67],"conducted":[68],"a":[70],"5-point":[71],"Likert":[72],"scale.":[73],"findings":[75],"indicate":[76],"that":[77,95],"although":[78],"offer":[81],"considerable":[82],"efficiency,":[83],"their":[84],"consistency":[85],"judgments":[88],"varies":[89],"substantially.":[90],"Moreover,":[91],"results":[93],"suggest":[94],"both":[96],"model":[98],"configuration":[99],"its":[101],"underlying":[102],"architecture":[103],"significantly":[104],"affect":[105],"outcomes.":[107],"Among":[108],"metric":[110],"categories,":[111],"LLM-as-a-Judge":[112],"appears":[113],"yield":[115],"highest":[117],"alignment":[118],"assessments,":[121],"suggesting":[122],"greater":[123],"this":[126],"approach.":[127]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-19T00:00:00"}
