{"id":"https://openalex.org/W4400484693","doi":"https://doi.org/10.1145/3663529.3663873","title":"Do Large Language Models Generate Similar Codes from Mutated Prompts? A Case Study of Gemini Pro","display_name":"Do Large Language Models Generate Similar Codes from Mutated Prompts? A Case Study of Gemini Pro","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4400484693","doi":"https://doi.org/10.1145/3663529.3663873"},"language":"en","primary_location":{"id":"doi:10.1145/3663529.3663873","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3663529.3663873","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":"Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3663529.3663873","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hetvi Patel","orcid":"https://orcid.org/0009-0009-5470-4488"},"institutions":[{"id":"https://openalex.org/I27674431","display_name":"Indian Institute of Technology Gandhinagar","ror":"https://ror.org/0036p5w23","country_code":"IN","type":"education","lineage":["https://openalex.org/I27674431"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Hetvi Patel","raw_affiliation_strings":["IIT Gandhinagar, Gandhinagar, India"],"raw_orcid":"https://orcid.org/0009-0009-5470-4488","affiliations":[{"raw_affiliation_string":"IIT Gandhinagar, Gandhinagar, India","institution_ids":["https://openalex.org/I27674431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044523353","display_name":"Kevin Amit Shah","orcid":"https://orcid.org/0009-0005-7328-2453"},"institutions":[{"id":"https://openalex.org/I27674431","display_name":"Indian Institute of Technology Gandhinagar","ror":"https://ror.org/0036p5w23","country_code":"IN","type":"education","lineage":["https://openalex.org/I27674431"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kevin Amit Shah","raw_affiliation_strings":["IIT Gandhinagar, Gandhinagar, India"],"raw_orcid":"https://orcid.org/0009-0005-7328-2453","affiliations":[{"raw_affiliation_string":"IIT Gandhinagar, Gandhinagar, India","institution_ids":["https://openalex.org/I27674431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067225281","display_name":"Shouvick Mondal","orcid":"https://orcid.org/0000-0002-0703-8728"},"institutions":[{"id":"https://openalex.org/I27674431","display_name":"Indian Institute of Technology Gandhinagar","ror":"https://ror.org/0036p5w23","country_code":"IN","type":"education","lineage":["https://openalex.org/I27674431"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shouvick Mondal","raw_affiliation_strings":["IIT Gandhinagar, Gandhinagar, India"],"raw_orcid":"https://orcid.org/0000-0002-0703-8728","affiliations":[{"raw_affiliation_string":"IIT Gandhinagar, Gandhinagar, India","institution_ids":["https://openalex.org/I27674431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27674431"],"apc_list":null,"apc_paid":null,"fwci":1.3245,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.83289768,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"671","last_page":"672"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.998199999332428,"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":0.998199999332428,"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":0.9894999861717224,"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/T13629","display_name":"Text Readability and Simplification","score":0.9884999990463257,"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":0.7266285419464111},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.43580466508865356},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38543927669525146},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34887540340423584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7266285419464111},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.43580466508865356},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38543927669525146},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34887540340423584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3663529.3663873","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3663529.3663873","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":"Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3663529.3663873","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3663529.3663873","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":"Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W4384026520"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"In":[0],"this":[1,57],"work,":[2],"we":[3,62,101,112],"delve":[4],"into":[5,151],"the":[6,23,51,64,97,105,117,124,132,145,152],"domain":[7],"of":[8,31,53,156],"source":[9,32],"code":[10,44,72,103,114,141,162],"similarity":[11],"detection":[12,42],"using":[13,96,116],"Large":[14],"Language":[15],"Models":[16],"(LLMs).":[17],"Our":[18,127],"investigation":[19],"is":[20],"motivated":[21],"by":[22],"necessity":[24],"to":[25,87,130,134],"identify":[26],"similarities":[27,115],"among":[28],"different":[29,90],"pieces":[30],"code,":[33],"a":[34,83],"critical":[35],"aspect":[36],"for":[37,56,71,104],"tasks":[38],"such":[39],"as":[40],"plagiarism":[41],"and":[43,78,80,107,154,160,164],"reuse.":[45],"We":[46],"specifically":[47],"focus":[48],"on":[49],"exploring":[50],"effectiveness":[52],"leveraging":[54],"LLMs":[55,136,157],"purpose.":[58],"To":[59],"achieve":[60],"this,":[61],"utilized":[63],"LLMSecEval":[65],"dataset,":[66],"comprising":[67],"150":[68],"NL":[69,93,109,147],"prompts":[70],"generation":[73],"across":[74],"two":[75],"languages:":[76],"C":[77],"Python,":[79],"employed":[81],"radamsa,":[82],"mutation-based":[84],"input":[85,146],"generator,":[86],"create":[88],"26":[89],"mutations":[91,143],"per":[92],"prompt.":[94],"Next,":[95],"Gemini":[98],"Pro":[99],"LLM,":[100],"generated":[102],"original":[106],"mutated":[108],"prompts.":[110],"Finally,":[111],"detect":[113],"recently":[118],"proposed":[119],"CodeBERTScore":[120],"metric":[121],"that":[122],"utilizes":[123],"CodeBERT":[125],"LLM.":[126],"experiment":[128],"aims":[129],"uncover":[131],"extent":[133],"which":[135],"can":[137],"consistently":[138],"generate":[139],"similar":[140],"despite":[142],"in":[144,158],"prompts,":[148],"providing":[149],"insights":[150],"robustness":[153],"generalizability":[155],"understanding":[159],"comparing":[161],"syntax":[163],"semantics.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}