{"id":"https://openalex.org/W4415926832","doi":"https://doi.org/10.48550/arxiv.2510.27565","title":"CodeAlignBench: Assessing Code Generation Models on Developer-Preferred Code Adjustments","display_name":"CodeAlignBench: Assessing Code Generation Models on Developer-Preferred Code Adjustments","publication_year":2025,"publication_date":"2025-10-31","ids":{"openalex":"https://openalex.org/W4415926832","doi":"https://doi.org/10.48550/arxiv.2510.27565"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2510.27565","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.27565","pdf_url":"https://arxiv.org/pdf/2510.27565","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/2510.27565","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089364065","display_name":"Forough Mehralian","orcid":"https://orcid.org/0000-0001-8969-5360","observed_orcids":["https://orcid.org/0000-0001-8969-5360"]},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehralian, Forough","raw_affiliation_strings":["Apple Inc. Seattle , WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple Inc. Seattle , WA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119204319","display_name":"Ryan Shar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shar, Ryan","raw_affiliation_strings":["Apple Inc. Seattle , WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple Inc. Seattle , WA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057575544","display_name":"James R. Rae","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rae, James R.","raw_affiliation_strings":["Apple Inc. Seattle , WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple Inc. Seattle , WA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128801561","display_name":"Alireza Hashemi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hashemi, Alireza","raw_affiliation_strings":["Apple Inc. Seattle , WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple Inc. Seattle , WA","institution_ids":["https://openalex.org/I4210153776"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210153776"],"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":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":0.0010999999940395355,"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/T10533","display_name":"Teaching and Learning Programming","score":0.0008999999845400453,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.6629999876022339},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.875},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.7239999771118164},{"id":"https://openalex.org/keywords/instruction-following","display_name":"instruction following","score":0.8339999914169312},{"id":"https://openalex.org/keywords/developer-preferences","display_name":"developer preferences","score":0.753000020980835},{"id":"https://openalex.org/keywords/program-refinement","display_name":"program refinement","score":0.6629999876022339},{"id":"https://openalex.org/keywords/interlingual-translation","display_name":"interlingual translation","score":0.593999981880188}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8823000192642212},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8223000168800354},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6876999735832214},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5943999886512756},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5378000140190125},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.5170999765396118},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.5116000175476074},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.49300000071525574},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.48919999599456787},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.40779998898506165},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3853999972343445},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3772999942302704},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3571000099182129},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2712000012397766},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.25110000371932983},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2510.27565","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.27565","pdf_url":"https://arxiv.org/pdf/2510.27565","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.2510.27565","doi":"https://doi.org/10.48550/arxiv.2510.27565","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.27565","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:2510.27565","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.27565","pdf_url":"https://arxiv.org/pdf/2510.27565","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/W4415926832.pdf","grobid_xml":"https://content.openalex.org/works/W4415926832.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W3177813494","https://openalex.org/W3195140297","https://openalex.org/W4385567149","https://openalex.org/W4388718089","https://openalex.org/W4389520295","https://openalex.org/W4392822190","https://openalex.org/W4404781195","https://openalex.org/W4410537502","https://openalex.org/W4411120240","https://openalex.org/W4412945109","https://openalex.org/W4416716405","https://openalex.org/W7125135101"],"related_works":["https://openalex.org/W4416887898","https://openalex.org/W4416716405","https://openalex.org/W4416553023","https://openalex.org/W4388747891","https://openalex.org/W4417296649","https://openalex.org/W4402835407","https://openalex.org/W4391835842","https://openalex.org/W7168828084","https://openalex.org/W4415622293","https://openalex.org/W7116946342"],"abstract_inverted_index":{"As":[0],"large":[1],"language":[2],"models":[3,120],"become":[4],"increasingly":[5],"capable":[6],"of":[7,29,57,124,129,139],"generating":[8],"code,":[9],"evaluating":[10],"their":[11,144],"performance":[12,125],"remains":[13],"a":[14,41,135],"complex":[15],"and":[16,33,49,79,113,146,150],"evolving":[17],"challenge.":[18],"Existing":[19],"benchmarks":[20],"primarily":[21],"focus":[22],"on":[23,54,86],"functional":[24],"correctness,":[25],"overlooking":[26],"the":[27,76,80],"diversity":[28],"real-world":[30],"coding":[31,59],"tasks":[32,101],"developer":[34],"expectations.":[35],"To":[36],"this":[37,90],"end,":[38],"we":[39,93],"introduce":[40],"multi-language":[42],"benchmark":[43,62,117],"that":[44,104,119],"evaluates":[45,63],"LLM":[46],"instruction-following":[47],"capabilities":[48],"is":[50],"extensible":[51],"to":[52,71,82],"operate":[53],"any":[55],"set":[56],"standalone":[58],"problems.":[60],"Our":[61,115,131],"instruction":[64],"following":[65],"in":[66],"two":[67],"key":[68],"settings:":[69],"adherence":[70],"pre-defined":[72],"constraints":[73],"specified":[74],"with":[75,99],"initial":[77],"problem,":[78],"ability":[81],"perform":[83],"refinements":[84],"based":[85],"follow-up":[87],"instructions.":[88],"For":[89],"paper's":[91],"analysis,":[92],"empirically":[94],"evaluated":[95],"our":[96],"benchmarking":[97,132],"pipeline":[98,133],"programming":[100],"from":[102,109],"LiveBench,":[103],"are":[105],"also":[106],"automatically":[107],"translated":[108],"Python":[110],"into":[111],"Java":[112],"JavaScript.":[114],"automated":[116],"reveals":[118],"exhibit":[121],"differing":[122],"levels":[123],"across":[126,148],"multiple":[127],"dimensions":[128],"instruction-following.":[130],"provides":[134],"more":[136],"comprehensive":[137],"evaluation":[138],"code":[140],"generation":[141,151],"models,":[142],"highlighting":[143],"strengths":[145],"limitations":[147],"languages":[149],"goals.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2025-11-05T00:00:00"}