{"id":"https://openalex.org/W4416098280","doi":"https://doi.org/10.48550/arxiv.2505.05063","title":"CodeMixBench: Evaluating Large Language Models on Code Generation with Code-Mixed Prompts","display_name":"CodeMixBench: Evaluating Large Language Models on Code Generation with Code-Mixed Prompts","publication_year":2025,"publication_date":"2025-05-08","ids":{"openalex":"https://openalex.org/W4416098280","doi":"https://doi.org/10.48550/arxiv.2505.05063"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.05063","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.05063","pdf_url":"https://arxiv.org/pdf/2505.05063","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.05063","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120338746","display_name":"Manik Sheokand","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I101407740","display_name":"Chandigarh University","ror":"https://ror.org/05t4pvx35","country_code":"IN","type":"education","lineage":["https://openalex.org/I101407740"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sheokand, Manik","raw_affiliation_strings":["Department of Computer Science Chandigarh University Punjab , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Chandigarh University Punjab , India","institution_ids":["https://openalex.org/I101407740"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120338747","display_name":"Parth Sawant","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sawant, Parth","raw_affiliation_strings":["Department of Technology Management and Innovation New York University New York , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Technology Management and Innovation New York University New York , USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9955999851226807,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9955999851226807,"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/T10028","display_name":"Topic Modeling","score":0.0020000000949949026,"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":0.0006000000284984708,"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/code-generation","display_name":"code generation","score":0.8420000076293945},{"id":"https://openalex.org/keywords/multilingual-code-generation","display_name":"multilingual code generation","score":0.7710000276565552},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7279999852180481},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.5920000076293945},{"id":"https://openalex.org/keywords/hinglish","display_name":"Hinglish","score":0.8050000071525574},{"id":"https://openalex.org/keywords/spanish-english","display_name":"Spanish-English","score":0.7689999938011169},{"id":"https://openalex.org/keywords/chinese-pinyin","display_name":"Chinese pinyin","score":0.8659999966621399},{"id":"https://openalex.org/keywords/prompt-robustness","display_name":"prompt robustness","score":0.7350000143051147},{"id":"https://openalex.org/keywords/model-size-effects","display_name":"model size effects","score":0.5299999713897705}],"concepts":[{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.7921000123023987},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7829999923706055},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.605400025844574},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.551800012588501},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5485000014305115},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5163000226020813},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45559999346733093},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4555000066757202},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3799999952316284},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3619000017642975},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2985999882221222},{"id":"https://openalex.org/C2988963302","wikidata":"https://www.wikidata.org/wiki/Q629206","display_name":"Program code","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.25690001249313354}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.05063","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.05063","pdf_url":"https://arxiv.org/pdf/2505.05063","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.05063","doi":"https://doi.org/10.48550/arxiv.2505.05063","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.05063","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.05063","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.05063","pdf_url":"https://arxiv.org/pdf/2505.05063","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416098280.pdf","grobid_xml":"https://content.openalex.org/works/W4416098280.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W3177813494","https://openalex.org/W3195140297","https://openalex.org/W4226287673","https://openalex.org/W4386185625","https://openalex.org/W4391272793","https://openalex.org/W4403571021","https://openalex.org/W4403796339","https://openalex.org/W4412889664","https://openalex.org/W4414281281"],"related_works":["https://openalex.org/W4415058563","https://openalex.org/W7131786218","https://openalex.org/W4416868356","https://openalex.org/W4403573295","https://openalex.org/W7118067677","https://openalex.org/W7168346062","https://openalex.org/W4307479317","https://openalex.org/W7123436778","https://openalex.org/W4388747891","https://openalex.org/W7169615406"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"achieved":[5],"remarkable":[6],"success":[7],"in":[8],"code":[9,16,70,108,152,163],"generation":[10,71,109,153,164],"tasks,":[11],"powering":[12],"various":[13],"applications":[14],"like":[15],"completion,":[17],"debugging,":[18],"and":[19,29,97,154,158],"programming":[20],"assistance.":[21],"However,":[22],"existing":[23],"benchmarks":[24],"such":[25],"as":[26],"HumanEval,":[27],"MBPP,":[28],"BigCodeBench":[30],"primarily":[31],"evaluate":[32,64,102],"LLMs":[33,68],"on":[34,69],"English-only":[35,130],"prompts,":[36],"overlooking":[37],"the":[38,65,84],"real-world":[39],"scenario":[40],"where":[41],"multilingual":[42,151],"developers":[43],"often":[44],"use":[45],"code-mixed":[46,73,121],"language":[47,86,92],"while":[48],"interacting":[49],"with":[50,132],"LLMs.":[51],"To":[52],"address":[53],"this":[54],"gap,":[55],"we":[56],"introduce":[57],"CodeMixBench,":[58],"a":[59,103,145],"novel":[60],"benchmark":[61],"designed":[62],"to":[63,114,128],"robustness":[66],"of":[67,88,106],"from":[72,112],"prompts.":[74],"Built":[75],"upon":[76],"BigCodeBench,":[77],"CodeMixBench":[78,143],"introduces":[79],"controlled":[80],"code-mixing":[81],"(CMD)":[82],"into":[83],"natural":[85],"parts":[87],"prompts":[89,122],"across":[90,169],"three":[91],"pairs:":[93],"Hinglish":[94],"(Hindi-English),":[95],"Spanish-English,":[96],"Chinese":[98],"Pinyin-English.":[99],"We":[100],"comprehensively":[101],"diverse":[104,170],"set":[105],"open-source":[107],"models":[110,165],"ranging":[111],"1.5B":[113],"15B":[115],"parameters.":[116],"Our":[117],"results":[118],"show":[119],"that":[120,166],"consistently":[123],"degrade":[124],"Pass@1":[125],"performance":[126,133],"compared":[127],"their":[129],"counterparts,":[131],"drops":[134],"increasing":[135],"under":[136],"higher":[137],"CMD":[138],"levels":[139],"for":[140,149,160],"smaller":[141],"models.":[142],"provides":[144],"realistic":[146],"evaluation":[147],"framework":[148],"studying":[150],"highlights":[155],"new":[156],"challenges":[157],"directions":[159],"building":[161],"robust":[162],"generalize":[167],"well":[168],"linguistic":[171],"settings.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}