{"id":"https://openalex.org/W4406892450","doi":"https://doi.org/10.1109/fllm63129.2024.10852484","title":"Adaptive Composite Accuracy Scoring for Domainspecific LLM Evaluation","display_name":"Adaptive Composite Accuracy Scoring for Domainspecific LLM Evaluation","publication_year":2024,"publication_date":"2024-11-26","ids":{"openalex":"https://openalex.org/W4406892450","doi":"https://doi.org/10.1109/fllm63129.2024.10852484"},"language":"en","primary_location":{"id":"doi:10.1109/fllm63129.2024.10852484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm63129.2024.10852484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 2nd International Conference on Foundation and Large Language Models (FLLM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jocelyn Shuang Ru Teh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jocelyn Shuang Ru Teh","raw_affiliation_strings":["Intel Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Eng Keong Koay","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Eng Keong Koay","raw_affiliation_strings":["Intel Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014399174","display_name":"Shin Wei Lim","orcid":"https://orcid.org/0009-0000-6214-6599"},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shin Wei Lim","raw_affiliation_strings":["Intel Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047504393","display_name":"Kuan Heng Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kuan Heng Lee","raw_affiliation_strings":["Intel Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028499291","display_name":"Mee Sim Lai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mee Sim Lai","raw_affiliation_strings":["Intel Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379084","display_name":"Myeong Soo Lee","orcid":"https://orcid.org/0000-0001-6651-7641"},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Meng Siong Lee","raw_affiliation_strings":["Intel Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5116057025","display_name":"Yuan Kuok Nee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuan Kuok Nee","raw_affiliation_strings":["Intel Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210158342"],"apc_list":null,"apc_paid":null,"fwci":0.3295,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.69748455,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"272","last_page":"279"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.7570000290870667,"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":0.7570000290870667,"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/computer-science","display_name":"Computer science","score":0.6055819988250732},{"id":"https://openalex.org/keywords/composite-number","display_name":"Composite number","score":0.4674820303916931},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36406564712524414},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3623729348182678},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13686853647232056}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6055819988250732},{"id":"https://openalex.org/C104779481","wikidata":"https://www.wikidata.org/wiki/Q50707","display_name":"Composite number","level":2,"score":0.4674820303916931},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36406564712524414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3623729348182678},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13686853647232056}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fllm63129.2024.10852484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm63129.2024.10852484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 2nd International Conference on Foundation and Large Language Models (FLLM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2890894339","https://openalex.org/W2946609015","https://openalex.org/W2963123047","https://openalex.org/W2964223283","https://openalex.org/W3201174429","https://openalex.org/W4385572046","https://openalex.org/W4389519254","https://openalex.org/W4391940656","https://openalex.org/W4401042689","https://openalex.org/W6749838110","https://openalex.org/W6762392948","https://openalex.org/W6777615688","https://openalex.org/W6782879696","https://openalex.org/W6809646742","https://openalex.org/W6810738896","https://openalex.org/W6846966473","https://openalex.org/W6852874933","https://openalex.org/W6853010253","https://openalex.org/W6854866820","https://openalex.org/W6857026196","https://openalex.org/W6858023062","https://openalex.org/W6862130063"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"With":[0,114],"the":[1,13,33,48,71,101,106,110,124,128,140,168,173],"increasing":[2],"demand":[3],"for":[4,63,177],"Large":[5],"Language":[6,51],"Models":[7],"(LLM)":[8],"deployment":[9,23],"across":[10],"different":[11],"industries,":[12],"need":[14,107],"to":[15,22,90,108,139,149,156],"evaluate":[16],"LLMs":[17,34],"with":[18,35,136,159],"benchmarking":[19,37,44,77,103,112,163],"datasets":[20,104,135],"prior":[21],"becomes":[24],"apparent.":[25],"Accuracy":[26,96,121],"scores":[27],"are":[28,60],"computed":[29],"individually":[30],"after":[31],"testing":[32],"multiple":[36],"datasets.":[38,113,164],"The":[39],"popular":[40],"publicly":[41],"available":[42],"general":[43],"datasets,":[45],"such":[46],"as":[47],"Massive":[49],"Multitask":[50],"Understanding":[52],"(MMLU)":[53],"dataset,":[54],"cover":[55],"multitude":[56],"of":[57,73,147,154],"domains,":[58],"which":[59],"less":[61],"suitable":[62,175],"domain-specific":[64,93,118,178],"LLM":[65,176],"use":[66],"cases.":[67],"This":[68,165],"paper":[69],"combines":[70],"goodness":[72],"objective-based":[74],"evaluation":[75,81],"(using":[76,82],"datasets)":[78],"and":[79,84,143,151],"subjective-based":[80],"LLM-as-a-judge)":[83],"devises":[85],"an":[86],"adaptive":[87],"weightage-based":[88],"method":[89],"compute":[91],"a":[92,115],"Weighted":[94,119],"Composite":[95,120],"Score":[97,122],"(WCAS)":[98],"extracted":[99],"from":[100],"existing":[102],"without":[105],"rerun":[109],"entire":[111],"more":[116],"refined":[117],"(WCAS),":[123],"result":[125],"shows":[126],"that":[127],"methodology":[129],"has":[130],"effectively":[131],"eliminated":[132],"47":[133],"MMLU":[134,162],"zero":[137],"relevancy":[138],"specific":[141],"domain":[142],"achieved":[144],"accuracy":[145],"refinement":[146],"up":[148,155],"12.4%":[150],"time":[152],"savings":[153],"87.2%":[157],"compared":[158],"running":[160],"57":[161],"approach":[166],"accelerates":[167],"decision-making":[169],"process":[170],"in":[171],"selecting":[172],"most":[174],"deployment.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-30T09:15:22.047038","created_date":"2025-10-10T00:00:00"}