{"id":"https://openalex.org/W4416034727","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.772","title":"MLAlgo-Bench: Can Machines Implement Machine Learning Algorithms?","display_name":"MLAlgo-Bench: Can Machines Implement Machine Learning Algorithms?","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034727","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.772"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.772","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.772","pdf_url":"https://aclanthology.org/2025.findings-emnlp.772.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: EMNLP 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-emnlp.772.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100413261","display_name":"Yunfei Wang","orcid":"https://orcid.org/0009-0004-2991-3935"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunfei Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014633813","display_name":"Yeqin Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yeqin Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009475618","display_name":"Yuyang Wu","orcid":"https://orcid.org/0009-0005-0727-5044"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuyang Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030625154","display_name":"L\u00fc Liang","orcid":"https://orcid.org/0000-0002-9892-8346"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058485829","display_name":"Phi Le Nguyen","orcid":"https://orcid.org/0000-0001-6547-7641"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Phi Le Nguyen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100369110","display_name":"Xiaoliang Wang","orcid":"https://orcid.org/0000-0001-7820-4706"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoliang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5065000009","display_name":"Cam-Tu Nguyen","orcid":"https://orcid.org/0009-0006-9484-6876"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen Cam-Tu","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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14298","last_page":"14329"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.12479999661445618,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.12479999661445618,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.03539999946951866,"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/T14347","display_name":"Big Data and Digital Economy","score":0.03500000014901161,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computational-learning-theory","display_name":"Computational learning theory","score":0.37400001287460327},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.30570000410079956},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.3028999865055084},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.29330000281333923},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.25540000200271606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6721000075340271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5306000113487244},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4912000000476837},{"id":"https://openalex.org/C50292564","wikidata":"https://www.wikidata.org/wiki/Q2462783","display_name":"Computational learning theory","level":3,"score":0.37400001287460327},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.24410000443458557},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.24310000240802765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.772","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.772","pdf_url":"https://aclanthology.org/2025.findings-emnlp.772.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.772","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.772","pdf_url":"https://aclanthology.org/2025.findings-emnlp.772.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034727.pdf","grobid_xml":"https://content.openalex.org/works/W4416034727.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"machine":[1,146],"learning":[2,147],"(ML)":[3],"application":[4],"continues":[5],"to":[6],"expand":[7],"across":[8],"diverse":[9],"fields,":[10],"there":[11],"is":[12,87],"a":[13,25,46,106,139,150],"rising":[14],"demand":[15],"for":[16,35,58,79,109,152,160],"ML":[17,33,59,64,77],"code":[18,34,57,78,164],"generation.In":[19],"this":[20,42],"paper,":[21],"we":[22,44],"aim":[23],"at":[24,167],"critical":[26],"research":[27],"question:":[28],"Can":[29],"machines":[30],"autonomously":[31],"generate":[32],"sophisticated,":[36],"human-designed":[37],"algorithms":[38,60],"or":[39],"solutions?To":[40],"answer":[41],"question,":[43],"introduce":[45,116],"novel":[47],"benchmark,":[48],"MLAlgo-Bench,":[49],"which":[50],"includes":[51],"two":[52],"challenging":[53],"tasks:":[54],"1)":[55],"Generating":[56],"including":[61],"both":[62],"traditional":[63],"and":[65,70,100,132,149,163],"modern":[66],"deep":[67],"learningbased":[68],"methods,":[69],"2)":[71],"Giving":[72],"humans":[73],"solution":[74],"sketches,":[75],"writing":[76],"solving":[80],"practical":[81],"tasks":[82],"in":[83,89],"Kaggle":[84,154],"competitions.This":[85],"benchmark":[86],"unique":[88],"its":[90],"focus":[91],"on":[92,144],"the":[93,135],"challenges":[94],"of":[95],"interpreting":[96],"intricate":[97],"human":[98],"instructions":[99],"producing":[101],"multi-step,":[102],"high-complexity":[103],"code,":[104],"offering":[105],"rigorous":[107],"test":[108],"current":[110],"Large":[111],"Language":[112],"Model":[113],"(LLM)":[114],"capabilities.We":[115],"an":[117],"automatic":[118],"evaluation":[119],"framework":[120],"with":[121],"comprehensive":[122],"metrics":[123],"such":[124],"as":[125],"task":[126,141],"pass":[127],"rate,":[128],"relative":[129],"performance":[130],"metric,":[131],"time":[133],"overhead.Currently,":[134],"top-performing":[136],"models":[137],"(Claude3.5-Sonnet)achieve":[138],"48.8%":[140],"completion":[142],"rate":[143],"realizing":[145],"algorithms,":[148],"21.6%rate":[151],"completing":[153],"competitions.Further":[155],"analysis":[156],"suggests":[157],"substantial":[158],"room":[159],"improvement.The":[161],"data":[162],"are":[165],"available":[166],"https://github.com/":[168],"WoilfWang/MLAlgo-Bench-Main.":[169]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}