{"id":"https://openalex.org/W7117165756","doi":"https://doi.org/10.1145/3756681.3756985","title":"Large Language Models as Robust Data Generators in Software Analytics: Are We There Yet?","display_name":"Large Language Models as Robust Data Generators in Software Analytics: Are We There Yet?","publication_year":2025,"publication_date":"2025-06-17","ids":{"openalex":"https://openalex.org/W7117165756","doi":"https://doi.org/10.1145/3756681.3756985"},"language":null,"primary_location":{"id":"doi:10.1145/3756681.3756985","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3756681.3756985","pdf_url":null,"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 29th International Conference on Evaluation and Assessment in Software Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3756681.3756985","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119234579","display_name":"Md. Abdul Awal","orcid":null},"institutions":[{"id":"https://openalex.org/I32625721","display_name":"University of Saskatchewan","ror":"https://ror.org/010x8gc63","country_code":"CA","type":"education","lineage":["https://openalex.org/I32625721"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Md. Abdul Awal","raw_affiliation_strings":["Software Research Lab, University of Saskatchewan, Saskatoon, Saskatchewan, Canada"],"raw_orcid":"https://orcid.org/0009-0006-5760-8211","affiliations":[{"raw_affiliation_string":"Software Research Lab, University of Saskatchewan, Saskatoon, Saskatchewan, Canada","institution_ids":["https://openalex.org/I32625721"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046862791","display_name":"Mrigank Rochan","orcid":"https://orcid.org/0000-0001-9513-6573"},"institutions":[{"id":"https://openalex.org/I32625721","display_name":"University of Saskatchewan","ror":"https://ror.org/010x8gc63","country_code":"CA","type":"education","lineage":["https://openalex.org/I32625721"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mrigank Rochan","raw_affiliation_strings":["University of Saskatchewan, Saskatoon, Saskatchewan, Canada"],"raw_orcid":"https://orcid.org/0000-0001-9513-6573","affiliations":[{"raw_affiliation_string":"University of Saskatchewan, Saskatoon, Saskatchewan, Canada","institution_ids":["https://openalex.org/I32625721"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chanchal K. Roy","orcid":"https://orcid.org/0000-0003-0519-6164"},"institutions":[{"id":"https://openalex.org/I32625721","display_name":"University of Saskatchewan","ror":"https://ror.org/010x8gc63","country_code":"CA","type":"education","lineage":["https://openalex.org/I32625721"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Chanchal K. Roy","raw_affiliation_strings":["Software Research Lab, University of Saskatchewan, Saskatoon, Saskatchewan, Canada"],"raw_orcid":"https://orcid.org/0000-0003-0519-6164","affiliations":[{"raw_affiliation_string":"Software Research Lab, University of Saskatchewan, Saskatoon, Saskatchewan, Canada","institution_ids":["https://openalex.org/I32625721"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.77540353,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1035","last_page":"1044"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.6869000196456909,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.6869000196456909,"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/T10260","display_name":"Software Engineering Research","score":0.03959999978542328,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.03099999949336052,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/adversarial-system","display_name":"Adversarial system","score":0.8734999895095825},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6643999814987183},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.6236000061035156},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5759999752044678},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.43529999256134033},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4343000054359436},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.39579999446868896},{"id":"https://openalex.org/keywords/software-metric","display_name":"Software metric","score":0.3952000141143799},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.3391000032424927}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8734999895095825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.786899983882904},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6643999814987183},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.6236000061035156},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5759999752044678},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5616000294685364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45239999890327454},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.43529999256134033},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4343000054359436},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.39579999446868896},{"id":"https://openalex.org/C82214349","wikidata":"https://www.wikidata.org/wiki/Q657339","display_name":"Software metric","level":5,"score":0.3952000141143799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38440001010894775},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C140547941","wikidata":"https://www.wikidata.org/wiki/Q7797194","display_name":"Threat model","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3199000060558319},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.3131999969482422},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.30480000376701355},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.3003999888896942},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.3000999987125397},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C62913178","wikidata":"https://www.wikidata.org/wiki/Q7554361","display_name":"Software security assurance","level":4,"score":0.27570000290870667},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.27059999108314514},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2694999873638153}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3756681.3756985","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3756681.3756985","pdf_url":null,"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 29th International Conference on Evaluation and Assessment in Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3756681.3756985","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3756681.3756985","pdf_url":null,"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 29th International Conference on Evaluation and Assessment in Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1964401032","https://openalex.org/W2905526464","https://openalex.org/W2949128310","https://openalex.org/W2970641574","https://openalex.org/W2996851481","https://openalex.org/W2997451752","https://openalex.org/W3000135256","https://openalex.org/W3011574394","https://openalex.org/W3013132080","https://openalex.org/W3098605233","https://openalex.org/W3101449015","https://openalex.org/W3104423855","https://openalex.org/W3105604018","https://openalex.org/W3170092793","https://openalex.org/W4220722393","https://openalex.org/W4284664377","https://openalex.org/W4285490465","https://openalex.org/W4312803897","https://openalex.org/W4319737124","https://openalex.org/W4320560161","https://openalex.org/W4384345639","https://openalex.org/W4389158416","https://openalex.org/W4389544307","https://openalex.org/W4393034946","https://openalex.org/W4394745253","https://openalex.org/W4394745967","https://openalex.org/W4398150831","https://openalex.org/W4400315178","https://openalex.org/W4400583026","https://openalex.org/W4401543590","https://openalex.org/W4401544263","https://openalex.org/W6930709120"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Model":[2],"(LLM)-generated":[3],"data":[4,17,45,69,90,172,207],"is":[5,13],"increasingly":[6],"used":[7,110],"in":[8,97,145,188,221],"software":[9,39,135,189,222],"analytics,":[10],"but":[11],"it":[12],"unclear":[14],"how":[15,43],"this":[16,77],"compares":[18],"to":[19,27,51,208],"human-written":[20,52,87,114,179],"data,":[21,53,117,180],"particularly":[22],"when":[23],"models":[24,95,210],"are":[25,212],"exposed":[26],"adversarial":[28,101,121,129,157,186,219],"scenarios.":[29],"Adversarial":[30],"attacks":[31,187,220],"can":[32,62],"compromise":[33],"the":[34,57,84,98,105,152,155,195,202],"reliability":[35],"and":[36,73,82,88,115,119,142,215],"security":[37],"of":[38,86,100,107,154,204,217],"systems,":[40],"so":[41],"understanding":[42],"LLM-generated":[44,68,89,116,171,205],"performs":[46],"under":[47],"these":[48],"conditions,":[49],"compared":[50],"which":[54],"serves":[55],"as":[56],"benchmark":[58],"for":[59,91,197],"model":[60],"performance,":[61],"provide":[63],"valuable":[64],"insights":[65],"into":[66,200],"whether":[67],"offers":[70],"similar":[71],"robustness":[72,106,184],"effectiveness.":[74],"To":[75],"address":[76],"gap,":[78],"we":[79,150],"systematically":[80],"evaluate":[81,104],"compare":[83],"quality":[85,153,203],"fine-tuning":[92],"robust":[93],"pre-trained":[94],"(PTMs)":[96],"context":[99],"attacks.":[102,122],"We":[103],"six":[108],"widely":[109],"PTMs,":[111],"fine-tuned":[112,169,177],"on":[113,170,178],"before":[118],"after":[120],"This":[123],"evaluation":[124],"employs":[125],"nine":[126],"state-of-the-art":[127],"(SOTA)":[128],"attack":[130],"techniques":[131],"across":[132],"three":[133],"popular":[134],"analytics":[136,190],"tasks:":[137],"clone":[138],"detection,":[139],"code":[140,146],"summarization,":[141],"sentiment":[143],"analysis":[144],"review":[147],"discussions.":[148],"Additionally,":[149],"analyze":[151],"generated":[156],"examples":[158],"using":[159],"eleven":[160],"similarity":[161],"metrics.":[162],"Our":[163,192],"findings":[164],"reveal":[165],"that":[166,211],"while":[167],"PTMs":[168],"perform":[173],"competitively":[174],"with":[175],"those":[176],"they":[181],"exhibit":[182],"less":[183],"against":[185],"tasks.":[191],"study":[193],"underscores":[194],"need":[196],"further":[198],"exploration":[199],"enhancing":[201],"training":[206],"develop":[209],"both":[213],"high-performing":[214],"capable":[216],"withstanding":[218],"analytics.":[223]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-12-24T00:00:00"}