{"id":"https://openalex.org/W4415004459","doi":"https://doi.org/10.1109/mlcad65511.2025.11189055","title":"hdl2v: A Code Translation Dataset for Enhanced LLM Verilog Generation","display_name":"hdl2v: A Code Translation Dataset for Enhanced LLM Verilog Generation","publication_year":2025,"publication_date":"2025-09-08","ids":{"openalex":"https://openalex.org/W4415004459","doi":"https://doi.org/10.1109/mlcad65511.2025.11189055"},"language":"en","primary_location":{"id":"doi:10.1109/mlcad65511.2025.11189055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlcad65511.2025.11189055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 ACM/IEEE 7th Symposium on Machine Learning for CAD (MLCAD)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053271274","display_name":"Charles C. Hong","orcid":"https://orcid.org/0000-0002-0424-8252"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Hong","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113379669","display_name":"Brendan Roberts","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brendan Roberts","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070744513","display_name":"Ho-Jung An","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huijae An","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119925276","display_name":"Alex Um","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Um","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119925277","display_name":"Advay Ratan","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Advay Ratan","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008683881","display_name":"Yakun Sophia Shao","orcid":"https://orcid.org/0000-0003-1811-5407"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yakun Sophia Shao","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.5335,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.97019167,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9952999949455261,"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":0.9952999949455261,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9556999802589417,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/verilog","display_name":"Verilog","score":0.8259999752044678},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6233999729156494},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.49970000982284546},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4625999927520752},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.3921999931335449},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.34060001373291016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8550000190734863},{"id":"https://openalex.org/C2779030575","wikidata":"https://www.wikidata.org/wiki/Q827773","display_name":"Verilog","level":3,"score":0.8259999752044678},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6290000081062317},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6233999729156494},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.49970000982284546},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4625999927520752},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.3921999931335449},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.34060001373291016},{"id":"https://openalex.org/C42143788","wikidata":"https://www.wikidata.org/wiki/Q173341","display_name":"Hardware description language","level":3,"score":0.3294999897480011},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.30239999294281006},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2922999858856201},{"id":"https://openalex.org/C151578736","wikidata":"https://www.wikidata.org/wiki/Q1251793","display_name":"Redundant code","level":4,"score":0.2782999873161316},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.27639999985694885},{"id":"https://openalex.org/C98183937","wikidata":"https://www.wikidata.org/wiki/Q2112188","display_name":"Program analysis","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlcad65511.2025.11189055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlcad65511.2025.11189055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 ACM/IEEE 7th Symposium on Machine Learning for CAD (MLCAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1983394510","https://openalex.org/W2477858827","https://openalex.org/W3027968530","https://openalex.org/W3031264475","https://openalex.org/W3129831491","https://openalex.org/W4379115941","https://openalex.org/W4388040405","https://openalex.org/W4392972103","https://openalex.org/W4393145520","https://openalex.org/W4402172087","https://openalex.org/W4403023865","https://openalex.org/W4403024064","https://openalex.org/W4407749900","https://openalex.org/W4409285487","https://openalex.org/W4409369309","https://openalex.org/W4410582555"],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"are":[4],"playing":[5],"an":[6],"increasingly":[7],"large":[8],"role":[9],"in":[10,35,88,107,156],"domains":[11],"such":[12],"as":[13],"code":[14,18,33,41],"generation,":[15,19],"including":[16],"hardware":[17,74],"where":[20],"Verilog":[21,32,66,91],"is":[22],"the":[23,27,38,61,84,127],"key":[24],"language.":[25],"However,":[26],"amount":[28,39,62],"of":[29,40,63,86,96,129,149],"publicly":[30],"available":[31,42,64],"pales":[34],"comparison":[36],"to":[37,59,104,125,144],"for":[43,159],"software":[44],"languages":[45],"like":[46],"Python.":[47],"In":[48],"this":[49],"work,":[50],"we":[51,82,138],"present":[52],"hdl2v":[53,87],"(\"HDL-to-Verilog\"),":[54],"a":[55,97,130],"dataset":[56,143],"which":[57,147],"seeks":[58],"increase":[60],"human-written":[65],"data":[67,112,131],"by":[68,93,102,135],"translating":[69],"or":[70,114],"compiling":[71],"three":[72],"other":[73],"description":[75],"languages\u2014VHDL,":[76],"Chisel,":[77],"and":[78,140],"PyMTL3\u2014to":[79],"Verilog.":[80],"Furthermore,":[81],"demonstrate":[83],"value":[85],"enhancing":[89],"LLM":[90],"generation":[92],"improving":[94],"performance":[95,128],"32":[98],"billion-parameter":[99],"open-weight":[100],"model":[101],"up":[103],"23%":[105],"(pass@10)":[106],"VerilogEvalV2,":[108],"without":[109],"utilizing":[110],"any":[111],"augmentation":[113],"knowledge":[115],"distillation":[116],"from":[117],"larger":[118],"models.":[119],"We":[120],"also":[121],"show":[122],"hdl2v\u2019s":[123],"ability":[124],"boost":[126],"augmentation-based":[132],"fine-tuning":[133],"approach":[134],"63%.":[136],"Finally,":[137],"characterize":[139],"analyze":[141],"our":[142],"better":[145,161],"understand":[146],"characteristics":[148],"HDL-to-Verilog":[150],"datasets":[151],"can":[152],"be":[153],"expanded":[154],"upon":[155],"future":[157],"work":[158],"even":[160],"performance.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2025-10-10T00:00:00"}