{"id":"https://openalex.org/W4414231275","doi":"https://doi.org/10.1109/sera65747.2025.11154488","title":"Metamorphic Testing for Fairness Evaluation in Large Language Models: Identifying Intersectional Bias in LLaMA and GPT","display_name":"Metamorphic Testing for Fairness Evaluation in Large Language Models: Identifying Intersectional Bias in LLaMA and GPT","publication_year":2025,"publication_date":"2025-05-29","ids":{"openalex":"https://openalex.org/W4414231275","doi":"https://doi.org/10.1109/sera65747.2025.11154488"},"language":"en","primary_location":{"id":"doi:10.1109/sera65747.2025.11154488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sera65747.2025.11154488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACIS 23rd International Conference on Software Engineering Research, Management and Applications (SERA)","raw_type":"proceedings-article"},"type":"conference-paper","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":"https://openalex.org/A5118120325","display_name":"Harishwar Reddy","orcid":null},"institutions":[{"id":"https://openalex.org/I186335123","display_name":"East Carolina University","ror":"https://ror.org/01vx35703","country_code":"US","type":"education","lineage":["https://openalex.org/I186335123"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harishwar Reddy","raw_affiliation_strings":["East Carolina University,Computer Science,Greenville,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East Carolina University,Computer Science,Greenville,USA","institution_ids":["https://openalex.org/I186335123"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050103951","display_name":"Madhusudan Srinivasan","orcid":"https://orcid.org/0000-0003-2228-1934"},"institutions":[{"id":"https://openalex.org/I186335123","display_name":"East Carolina University","ror":"https://ror.org/01vx35703","country_code":"US","type":"education","lineage":["https://openalex.org/I186335123"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Madhusudan Srinivasan","raw_affiliation_strings":["East Carolina University,Computer Science,Greenville,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East Carolina University,Computer Science,Greenville,USA","institution_ids":["https://openalex.org/I186335123"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083120673","display_name":"Upulee Kanewala","orcid":"https://orcid.org/0000-0002-5954-1616"},"institutions":[{"id":"https://openalex.org/I11874761","display_name":"University of North Florida","ror":"https://ror.org/01j903a45","country_code":"US","type":"education","lineage":["https://openalex.org/I11874761"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Upulee Kanewala","raw_affiliation_strings":["University of North Florida,Computer Science,Jacksonville,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Florida,Computer Science,Jacksonville,USA","institution_ids":["https://openalex.org/I11874761"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.195,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.97502356,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"239","last_page":"246"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9544000029563904,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9544000029563904,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6442000269889832},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.557200014591217},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.3808000087738037},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3587999939918518},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.3330000042915344},{"id":"https://openalex.org/keywords/inequity-aversion","display_name":"Inequity aversion","score":0.3221000134944916}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6442000269889832},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6004999876022339},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.557200014591217},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3781000077724457},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36390000581741333},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3587999939918518},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3366999924182892},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.33379998803138733},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C194959371","wikidata":"https://www.wikidata.org/wiki/Q17056235","display_name":"Inequity aversion","level":3,"score":0.3221000134944916},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.31869998574256897},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30809998512268066},{"id":"https://openalex.org/C6571938","wikidata":"https://www.wikidata.org/wiki/Q3274486","display_name":"Omitted-variable bias","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.2750000059604645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sera65747.2025.11154488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sera65747.2025.11154488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACIS 23rd International Conference on Software Engineering Research, Management and Applications (SERA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2903744551","https://openalex.org/W2907879020","https://openalex.org/W3035671939","https://openalex.org/W3142064846","https://openalex.org/W4210972988","https://openalex.org/W4223627220","https://openalex.org/W4386730022","https://openalex.org/W4386810265","https://openalex.org/W4389209181","https://openalex.org/W4393407165","https://openalex.org/W4399528455","https://openalex.org/W4401905935","https://openalex.org/W4403865042"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1,10],"Models":[2],"(LLMs)":[3],"have":[4],"made":[5],"significant":[6],"strides":[7],"in":[8,22,35,56,109,114,137,152],"Natural":[9],"Processing":[11],"but":[12],"remain":[13],"vulnerable":[14],"to":[15,51,69,116,143],"fairness-related":[16],"issues,":[17],"often":[18],"reflecting":[19],"biases":[20,27,147],"inherent":[21],"their":[23],"training":[24],"data.":[25],"These":[26],"pose":[28],"risks,":[29],"particularly":[30],"when":[31],"LLMs":[32],"are":[33],"deployed":[34],"sensitive":[36,125],"areas":[37],"such":[38],"as":[39],"healthcare,":[40],"finance,":[41],"and":[42,60,73,88,95,118,120,145,148],"law.":[43],"This":[44,132],"paper":[45],"introduces":[46],"a":[47,62,76,140],"metamorphic":[48,66],"testing":[49,136],"approach":[50,142],"systematically":[52],"identify":[53],"fairness":[54,100,130,135],"bugs":[55],"LLMs.":[57],"We":[58],"define":[59],"apply":[61],"set":[63],"of":[64,107,124],"fairness-oriented":[65],"relations":[67],"(MRs)":[68],"assess":[70],"the":[71,105],"LLaMA":[72],"GPT":[74],"model,":[75],"state-of-the-art":[77],"LLM,":[78],"across":[79],"diverse":[80],"demographic":[81],"inputs.":[82],"Our":[83],"methodology":[84],"includes":[85],"generating":[86],"source":[87],"follow-up":[89],"test":[90],"cases":[91],"for":[92,99],"each":[93],"MR":[94],"analyzing":[96],"model":[97,150],"responses":[98],"violations.":[101],"The":[102],"results":[103],"demonstrate":[104],"effectiveness":[106],"MT":[108],"exposing":[110],"bias":[111],"patterns,":[112],"especially":[113],"relation":[115],"tone":[117],"sentiment,":[119],"highlight":[121],"specific":[122],"intersections":[123],"attributes":[126],"that":[127],"frequently":[128],"reveal":[129],"faults.":[131],"research":[133],"improves":[134],"LLMs,":[138],"providing":[139],"structured":[141],"detect":[144],"mitigate":[146],"improve":[149],"robustness":[151],"fairness-sensitive":[153],"applications.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}