{"id":"https://openalex.org/W4416035208","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.160","title":"VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation","display_name":"VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035208","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.160"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.160","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.160","pdf_url":"https://aclanthology.org/2025.findings-emnlp.160.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.160.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108988983","display_name":"Yuansheng Ni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuansheng Ni","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053562090","display_name":"Ping Nie","orcid":"https://orcid.org/0000-0002-8640-8685"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ping Nie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021577237","display_name":"Kai Zou","orcid":"https://orcid.org/0000-0001-5795-6132"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Zou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086600391","display_name":"Xiang Yue","orcid":"https://orcid.org/0000-0003-4547-1685"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Yue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103103242","display_name":"Wenhu Chen","orcid":"https://orcid.org/0000-0002-8609-7821"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenhu Chen","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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2956","last_page":"2983"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13650","display_name":"Computational Physics and Python Applications","score":0.3206000030040741,"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/T13650","display_name":"Computational Physics and Python Applications","score":0.3206000030040741,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.08829999715089798,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10126","display_name":"Logic, programming, and type systems","score":0.0406000018119812,"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/python","display_name":"Python (programming language)","score":0.6780999898910522},{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.5914999842643738},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5644999742507935},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.35899999737739563},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3393000066280365},{"id":"https://openalex.org/keywords/data-visualization","display_name":"Data visualization","score":0.3181999921798706}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6780999898910522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6694999933242798},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.5914999842643738},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5734999775886536},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5644999742507935},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.35899999737739563},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.35569998621940613},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3393000066280365},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.31850001215934753},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.3181999921798706},{"id":"https://openalex.org/C73752529","wikidata":"https://www.wikidata.org/wiki/Q79872","display_name":"Object-oriented programming","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.160","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.160","pdf_url":"https://aclanthology.org/2025.findings-emnlp.160.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.160","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.160","pdf_url":"https://aclanthology.org/2025.findings-emnlp.160.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/W4416035208.pdf","grobid_xml":"https://content.openalex.org/works/W4416035208.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1,72],"models":[2,86,117],"(LLMs)":[3],"often":[4],"struggle":[5],"with":[6,70],"visualization":[7,52],"tasks":[8],"like":[9,118],"plotting":[10,64],"diagrams,":[11],"charts,":[12],"where":[13],"success":[14],"depends":[15],"on":[16,96,104],"both":[17],"code":[18,34,65,90,140],"correctness":[19],"and":[20,28,39,53,74,77,101,111],"visual":[21],"semantics.Existing":[22],"instruction-tuning":[23],"datasets":[24],"lack":[25],"executiongrounded":[26],"supervision":[27],"offer":[29],"limited":[30],"support":[31],"for":[32,50,136],"iterative":[33,128],"correction,":[35],"resulting":[36],"in":[37],"fragile":[38],"unreliable":[40],"plot":[41],"generation.We":[42],"present":[43],"VisCode-200K,":[44],"a":[45,122],"large-scale":[46],"instruction":[47],"tuning":[48],"dataset":[49],"Python-based":[51],"self-correction.It":[54],"contains":[55],"over":[56],"200K":[57],"examples":[58],"from":[59,66,83],"two":[60],"sources:":[61],"(1)":[62],"validated":[63],"open-source":[67,109],"repositories,":[68],"paired":[69],"natural":[71],"instructions":[73],"rendered":[75],"plots;":[76],"(2)":[78],"45K":[79],"multi-turn":[80],"correction":[81],"dialogues":[82],"Code-Feedback,":[84],"enabling":[85],"to":[87,98,126],"revise":[88],"faulty":[89],"using":[91],"runtime":[92],"feedback.We":[93],"fine-tune":[94],"Qwen2.5-Coder-Instruct":[95],"VisCode-200K":[97],"create":[99],"VisCoder,":[100],"evaluate":[102],"it":[103],"PandasPlotBench.VisCoder":[105],"significantly":[106],"outperforms":[107],"strong":[108],"baselines":[110],"approaches":[112],"the":[113,131],"performance":[114],"of":[115,133],"proprietary":[116],"GPT-4o-mini.We":[119],"further":[120],"adopt":[121],"selfdebug":[123],"evaluation":[124],"protocol":[125],"assess":[127],"repair,":[129],"demonstrating":[130],"benefits":[132],"feedbackdriven":[134],"learning":[135],"executable,":[137],"visually":[138],"accurate":[139],"generation.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}