{"id":"https://openalex.org/W7125899555","doi":"https://doi.org/10.1109/ase63991.2025.00385","title":"LLMorph: Automated Metamorphic Testing of Large Language Models","display_name":"LLMorph: Automated Metamorphic Testing of Large Language Models","publication_year":2025,"publication_date":"2025-11-16","ids":{"openalex":"https://openalex.org/W7125899555","doi":"https://doi.org/10.1109/ase63991.2025.00385"},"language":null,"primary_location":{"id":"doi:10.1109/ase63991.2025.00385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ase63991.2025.00385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 40th IEEE/ACM International Conference on Automated Software Engineering (ASE)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2603.23611","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124146024","display_name":"Steven Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"Steven Cho","raw_affiliation_strings":["University of Auckland,Auckland,New Zealand"],"affiliations":[{"raw_affiliation_string":"University of Auckland,Auckland,New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011541744","display_name":"Stefano Ruberto","orcid":"https://orcid.org/0000-0001-8666-2782"},"institutions":[{"id":"https://openalex.org/I2800387288","display_name":"European Commission","ror":"https://ror.org/00k4n6c32","country_code":"BE","type":"government","lineage":["https://openalex.org/I1320481043","https://openalex.org/I2800387288"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Stefano Ruberto","raw_affiliation_strings":["JRC European Commission,Ispra,Italy"],"affiliations":[{"raw_affiliation_string":"JRC European Commission,Ispra,Italy","institution_ids":["https://openalex.org/I2800387288"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068101658","display_name":"Valerio Terragni","orcid":"https://orcid.org/0000-0001-5885-9297"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Valerio Terragni","raw_affiliation_strings":["University of Auckland,Auckland,New Zealand"],"affiliations":[{"raw_affiliation_string":"University of Auckland,Auckland,New Zealand","institution_ids":["https://openalex.org/I154130895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5124146024"],"corresponding_institution_ids":["https://openalex.org/I154130895"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8463812,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4102","last_page":"4105"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.33709999918937683,"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/T10028","display_name":"Topic Modeling","score":0.33709999918937683,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.16830000281333923,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.041200000792741776,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/correctness","display_name":"Correctness","score":0.7804999947547913},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6294999718666077},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.569100022315979},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4645000100135803},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4442000091075897},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.3813999891281128},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3573000133037567},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.35600000619888306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8098000288009644},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7804999947547913},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6294999718666077},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.569100022315979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5612999796867371},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5145999789237976},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4645000100135803},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4442000091075897},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4163999855518341},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40630000829696655},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3573000133037567},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.34380000829696655},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33739998936653137},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.3215999901294708},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C169168650","wikidata":"https://www.wikidata.org/wiki/Q1675637","display_name":"Keyword-driven testing","level":5,"score":0.29789999127388},{"id":"https://openalex.org/C182122060","wikidata":"https://www.wikidata.org/wiki/Q6752328","display_name":"Manual testing","level":5,"score":0.2969000041484833},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.29660001397132874},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.28540000319480896},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C148027188","wikidata":"https://www.wikidata.org/wiki/Q907375","display_name":"Unit testing","level":3,"score":0.2554999887943268},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ase63991.2025.00385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ase63991.2025.00385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 40th IEEE/ACM International Conference on Automated Software Engineering (ASE)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2603.23611","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.23611","pdf_url":"https://arxiv.org/pdf/2603.23611","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2603.23611","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.23611","pdf_url":"https://arxiv.org/pdf/2603.23611","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7125899555.pdf","grobid_xml":"https://content.openalex.org/works/W7125899555.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2041713059","https://openalex.org/W2782311202","https://openalex.org/W4391136507","https://openalex.org/W4401905935","https://openalex.org/W4406798194","https://openalex.org/W4415746319","https://openalex.org/W4415799085"],"related_works":[],"abstract_inverted_index":{"Automated":[0],"testing":[1,34,141],"is":[2,85,172,179],"essential":[3],"for":[4,21,38],"evaluating":[5],"and":[6,89,109,126,147],"improving":[7],"the":[8,16,78,95,106],"reliability":[9],"of":[10,18,72,80,97,112,128],"Large":[11],"Language":[12],"Models":[13],"(LLMs),":[14],"yet":[15],"lack":[17],"automated":[19,33],"oracles":[20],"verifying":[22],"output":[23],"correctness":[24],"remains":[25],"a":[26],"key":[27],"challenge.":[28],"We":[29],"present":[30],"LLMorph,":[31,113],"an":[32],"tool":[35,169],"specifically":[36],"designed":[37],"LLMs":[39],"performing":[40],"NLP":[41,99,124,139],"tasks,":[42],"which":[43],"leverages":[44],"Metamorphic":[45,59],"Testing":[46],"(MT)":[47],"to":[48,62,93,121],"uncover":[49],"faulty":[50],"behaviors":[51,166],"without":[52,77],"relying":[53],"on":[54],"human-labeled":[55],"data.":[56,83],"MT":[57],"uses":[58],"Relations":[60],"(MRs)":[61],"generate":[63],"follow-up":[64],"inputs":[65],"from":[66],"source":[67,170],"test":[68,154],"input,":[69],"enabling":[70],"detection":[71],"inconsistencies":[73],"in":[74,161],"model":[75,165],"outputs":[76],"need":[79],"expensive":[81],"labelled":[82],"LLMorph":[84],"aimed":[86],"at":[87,167,174,181],"researchers":[88],"developers":[90],"who":[91],"want":[92],"evaluate":[94],"robustness":[96],"LLM-based":[98],"systems.":[100],"In":[101,130],"this":[102],"paper,":[103],"we":[104,133],"detail":[105],"design,":[107],"implementation,":[108],"practical":[110],"usage":[111],"demonstrating":[114],"how":[115],"it":[116],"can":[117],"be":[118],"easily":[119],"extended":[120],"any":[122],"LLM,":[123],"task,":[125],"set":[127],"MRs.":[129],"our":[131],"evaluation,":[132],"applied":[134],"36":[135],"MRs":[136],"across":[137],"four":[138],"benchmarks,":[140],"three":[142],"state-of-the-art":[143],"LLMs:":[144],"GPT-4,":[145],"LLAMA3,":[146],"HERMES":[148],"2.":[149],"This":[150],"produced":[151],"over":[152],"561,000":[153],"executions.":[155],"The":[156],"results":[157],"demonstrate":[158],"LLMorph\u2019s":[159],"effectiveness":[160],"automatically":[162],"exposing":[163],"incorrect":[164],"scale.The":[168],"code":[171],"available":[173,180],"https://github.com/steven-b-cho/llmorph.":[175],"A":[176],"screencast":[177],"demo":[178],"https://youtu.be/sHmqdieCfw4.":[182]},"counts_by_year":[],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2026-01-29T00:00:00"}