{"id":"https://openalex.org/W4412887691","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1133","title":"DynaCode: A Dynamic Complexity-Aware Code Benchmark for Evaluating Large Language Models in Code Generation","display_name":"DynaCode: A Dynamic Complexity-Aware Code Benchmark for Evaluating Large Language Models in Code Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887691","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1133"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1133","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1133","pdf_url":"https://aclanthology.org/2025.findings-acl.1133.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.1133.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101518021","display_name":"Wenhao Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenhao Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073311852","display_name":"Jinhao Duan","orcid":"https://orcid.org/0000-0001-7045-9376"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinhao Duan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064200359","display_name":"Chunchen Wei","orcid":"https://orcid.org/0000-0001-9207-5365"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chunchen Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425448","display_name":"Li Zhang","orcid":"https://orcid.org/0000-0001-7914-0679"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100333755","display_name":"Yue Zhang","orcid":"https://orcid.org/0000-0002-7786-0231"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078434437","display_name":"Keshuai Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaidi Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21980","last_page":"21997"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.996399998664856,"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":0.996399998664856,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9700000286102295,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9620000123977661,"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":0.8481347560882568},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7248803377151489},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.6829306483268738},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.6680718660354614},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6499809622764587},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4523405432701111},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32049477100372314},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12953084707260132}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8481347560882568},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7248803377151489},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6829306483268738},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.6680718660354614},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6499809622764587},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4523405432701111},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32049477100372314},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12953084707260132},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1133","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1133","pdf_url":"https://aclanthology.org/2025.findings-acl.1133.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.1133","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1133","pdf_url":"https://aclanthology.org/2025.findings-acl.1133.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887691.pdf","grobid_xml":"https://content.openalex.org/works/W4412887691.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2056396287","https://openalex.org/W2163672025","https://openalex.org/W2048831961","https://openalex.org/W1606349578","https://openalex.org/W4399567378"],"abstract_inverted_index":{"The":[0],"rapid":[1],"advancement":[2],"of":[3,23,43,70,103,113,125],"large":[4],"language":[5],"models":[6],"(LLMs)":[7],"has":[8],"significantly":[9],"improved":[10],"their":[11,162],"performance":[12,123,138],"in":[13],"code":[14,18,82,97,104,134,174],"generation":[15,135],"tasks.However,":[16],"existing":[17],"benchmarks":[19],"remain":[20],"static,":[21],"consisting":[22],"fixed":[24],"datasets":[25],"with":[26,137],"predefined":[27],"problems.This":[28],"makes":[29],"them":[30],"vulnerable":[31],"to":[32,45,49,92,107,127,130,147],"memorization":[33],"during":[34],"training,":[35],"where":[36],"LLMs":[37,74,119],"recall":[38],"specific":[39],"test":[40],"cases":[41],"instead":[42],"generalizing":[44],"new":[46],"problems,":[47],"leading":[48],"data":[50],"contamination":[51],"and":[52,84,110,172],"unreliable":[53],"evaluation":[54,173],"results.To":[55],"address":[56],"these":[57],"issues,":[58],"we":[59,155],"introduce":[60],"DynaCode,":[61],"a":[62,77,132],"dynamic,":[63],"complexity-aware":[64,78],"benchmark":[65,171],"that":[66],"overcomes":[67],"the":[68],"limitations":[69],"static":[71,133],"datasets.Dyna-Code":[72],"evaluates":[73],"systematically":[75],"using":[76],"metric,":[79],"incorporating":[80],"both":[81],"complexity":[83,142],"call-graph":[85],"structures.Dy-naCode":[86],"achieves":[87],"large-scale":[88],"diversity,":[89],"generating":[90],"up":[91],"189":[93],"million":[94],"unique":[95],"nested":[96,169],"problems":[98],"across":[99],"four":[100],"distinct":[101],"levels":[102],"complexity,":[105],"referred":[106],"as":[108,141],"units,":[109],"16":[111],"types":[112],"call":[114,153],"graphs.Results":[115],"on":[116],"12":[117],"latest":[118],"show":[120],"an":[121],"average":[122],"drop":[124],"16.8%":[126],"45.7%":[128],"compared":[129],"MBPP+,":[131],"benchmark,":[136],"progressively":[139],"decreasing":[140],"increases.This":[143],"demonstrates":[144],"DynaCode's":[145],"ability":[146],"effectively":[148],"differentiate":[149],"LLMs.Additionally,":[150],"by":[151],"leveraging":[152],"graphs,":[154],"gain":[156],"insights":[157],"into":[158],"LLM":[159],"behavior,":[160],"particularly":[161],"preference":[163],"for":[164],"handling":[165],"subfunction":[166],"interactions":[167],"within":[168],"code.Our":[170],"are":[175],"available":[176],"at":[177],"https://github.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}