{"id":"https://openalex.org/W7202291206","doi":"https://doi.org/10.18653/2026.emnlp-main.1038","title":"VisEditBench: Can Vision-Language Models Edit Visualization Code from Multimodal Feedback?","display_name":"VisEditBench: Can Vision-Language Models Edit Visualization Code from Multimodal Feedback?","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7202291206","doi":"https://doi.org/10.18653/2026.emnlp-main.1038"},"language":"en","primary_location":{"id":"doi:10.18653/2026.emnlp-main.1038","doi":"https://doi.org/10.18653/2026.emnlp-main.1038","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1038","pdf_url":"https://aclanthology.org/2026.emnlp-main.1038.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.emnlp-main.1038.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136865855","display_name":"Mizanur Rahman","orcid":"https://orcid.org/0009-0008-2627-8664","observed_orcids":["https://orcid.org/0009-0008-2627-8664"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]},{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["CA","SG","US"],"is_corresponding":false,"raw_author_name":"Mizanur Rahman","raw_affiliation_strings":["York University $ Nanyang Technological University \u00b6 Salesforce AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"York University $ Nanyang Technological University \u00b6 Salesforce AI Research","institution_ids":["https://openalex.org/I172675005","https://openalex.org/I192455969","https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146981123","display_name":"Arshia Azimlu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]},{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["CA","SG","US"],"is_corresponding":false,"raw_author_name":"Arshia Azimlu","raw_affiliation_strings":["York University $ Nanyang Technological University \u00b6 Salesforce AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"York University $ Nanyang Technological University \u00b6 Salesforce AI Research","institution_ids":["https://openalex.org/I172675005","https://openalex.org/I192455969","https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015460993","display_name":"Shadikur Rahman","orcid":"https://orcid.org/0000-0001-8844-3575","observed_orcids":["https://orcid.org/0000-0001-8844-3575"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]},{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["CA","SG","US"],"is_corresponding":false,"raw_author_name":"Shadikur Rahman","raw_affiliation_strings":["York University $ Nanyang Technological University \u00b6 Salesforce AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"York University $ Nanyang Technological University \u00b6 Salesforce AI Research","institution_ids":["https://openalex.org/I172675005","https://openalex.org/I192455969","https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069546450","display_name":"Md Tahmid Rahman Laskar","orcid":"https://orcid.org/0009-0001-7880-299X","observed_orcids":["https://orcid.org/0009-0001-7880-299X"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]},{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["CA","SG","US"],"is_corresponding":false,"raw_author_name":"Md Tahmid Rahman Laskar","raw_affiliation_strings":["York University $ Nanyang Technological University \u00b6 Salesforce AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"York University $ Nanyang Technological University \u00b6 Salesforce AI Research","institution_ids":["https://openalex.org/I172675005","https://openalex.org/I192455969","https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138024665","display_name":"Amran Bhuiyan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]},{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["CA","SG","US"],"is_corresponding":false,"raw_author_name":"Amran Bhuiyan","raw_affiliation_strings":["York University $ Nanyang Technological University \u00b6 Salesforce AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"York University $ Nanyang Technological University \u00b6 Salesforce AI Research","institution_ids":["https://openalex.org/I172675005","https://openalex.org/I192455969","https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005443526","display_name":"Shafiq Joty","orcid":"https://orcid.org/0000-0002-9222-2641","observed_orcids":["https://orcid.org/0000-0002-9222-2641"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shafiq Joty","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5067722075","display_name":"Enamul Hoque","orcid":"https://orcid.org/0000-0002-9789-6645","observed_orcids":["https://orcid.org/0000-0002-9789-6645"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]},{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["CA","SG","US"],"is_corresponding":false,"raw_author_name":"Enamul Hoque Prince","raw_affiliation_strings":["York University $ Nanyang Technological University \u00b6 Salesforce AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"York University $ Nanyang Technological University \u00b6 Salesforce AI Research","institution_ids":["https://openalex.org/I172675005","https://openalex.org/I192455969","https://openalex.org/I4210155268"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.7683,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.95143806,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"23828","last_page":"23846"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7534000277519226,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7534000277519226,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10799","display_name":"Data Visualization and Analytics","score":0.2053000032901764,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10260","display_name":"Software Engineering Research","score":0.011300000362098217,"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/vision-language-models","display_name":"vision-language models","score":0.9539999961853027},{"id":"https://openalex.org/keywords/multimodal-feedback","display_name":"multimodal feedback","score":0.8270000219345093},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.7149999737739563},{"id":"https://openalex.org/keywords/style-adaptation","display_name":"style adaptation","score":0.7239999771118164},{"id":"https://openalex.org/keywords/gpt-4o","display_name":"GPT-4o","score":0.8169999718666077},{"id":"https://openalex.org/keywords/visualization-authoring","display_name":"visualization authoring","score":0.5440000295639038}],"concepts":[{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.9065999984741211},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8434000015258789},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5800999999046326},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.531000018119812},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.48539999127388},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4846000075340271},{"id":"https://openalex.org/C190812933","wikidata":"https://www.wikidata.org/wiki/Q28923","display_name":"Chart","level":2,"score":0.4097000062465668},{"id":"https://openalex.org/C64073096","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Interactive visualization","level":3,"score":0.4066999852657318},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3944999873638153},{"id":"https://openalex.org/C185578843","wikidata":"https://www.wikidata.org/wiki/Q10609775","display_name":"Information visualization","level":3,"score":0.37940001487731934},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3790999948978424},{"id":"https://openalex.org/C4379982","wikidata":"https://www.wikidata.org/wiki/Q1273511","display_name":"Software visualization","level":5,"score":0.36719998717308044},{"id":"https://openalex.org/C14669888","wikidata":"https://www.wikidata.org/wiki/Q4014850","display_name":"Creative visualization","level":3,"score":0.34929999709129333},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3427000045776367},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30219998955726624},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2793000042438507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2736000120639801},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2644999921321869},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.emnlp-main.1038","doi":"https://doi.org/10.18653/2026.emnlp-main.1038","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1038","pdf_url":"https://aclanthology.org/2026.emnlp-main.1038.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2608.10408","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.10408","pdf_url":"https://arxiv.org/pdf/2608.10408","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.2608.10408","doi":"https://doi.org/10.48550/arxiv.2608.10408","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.10408","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":"doi:10.18653/2026.emnlp-main.1038","doi":"https://doi.org/10.18653/2026.emnlp-main.1038","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1038","pdf_url":"https://aclanthology.org/2026.emnlp-main.1038.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310728","display_name":"Centre International de Recherche sur le Cancer","ror":"https://ror.org/00v452281"},{"id":"https://openalex.org/F4320314000","display_name":"Compute Canada","ror":"https://ror.org/03ty8yr27"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7202291206.pdf","grobid_xml":"https://content.openalex.org/works/W7202291206.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2751448157","https://openalex.org/W2947973062","https://openalex.org/W4226277810","https://openalex.org/W4378473094","https://openalex.org/W4386185625","https://openalex.org/W4387561528","https://openalex.org/W4389156632","https://openalex.org/W4390307100","https://openalex.org/W4401306886","https://openalex.org/W4403322180","https://openalex.org/W4405655184","https://openalex.org/W4414281281","https://openalex.org/W4416373998"],"related_works":["https://openalex.org/W4416035208","https://openalex.org/W7102405682","https://openalex.org/W7221174045","https://openalex.org/W7161581718","https://openalex.org/W7125200320","https://openalex.org/W6979371799","https://openalex.org/W7138125974","https://openalex.org/W4409346427","https://openalex.org/W7127309001","https://openalex.org/W7167589897"],"abstract_inverted_index":{"Vision-language":[0],"models":[1,77,94,127],"(VLMs)":[2],"have":[3],"shown":[4],"strong":[5,145],"capabilities":[6],"in":[7,63],"generating":[8],"visualization":[9,17,44,59,65,79,108,183],"code":[10,45,80,96,109],"from":[11,41,47,171],"textual":[12,88],"or":[13,31,83],"visual":[14],"specifications.However,":[15],"real-world":[16],"authoring":[18],"is":[19,131],"inherently":[20],"iterative:":[21],"users":[22],"frequently":[23],"revise":[24,78],"existing":[25],"visualizations":[26],"to":[27,34,97,173],"repair":[28],"flawed":[29],"charts":[30,85],"adapt":[32],"them":[33],"desired":[35],"styles.Existing":[36],"benchmarks":[37],"primarily":[38],"evaluate":[39],"generation":[40],"scratch,":[42],"leaving":[43],"editing":[46,110,153],"multimodal":[48],"feedback":[49,180],"largely":[50],"unexplored.We":[51],"introduce":[52],"VisEditBench,":[53],"a":[54,99,144,151],"benchmark":[55],"of":[56,122,178],"1,395":[57],"human-annotated":[58],"code-editing":[60],"tasks":[61],"grounded":[62,136],"realistic":[64],"workflows":[66],"and":[67,90,160],"failure":[68],"cases.VisEditBench":[69],"covers":[70],"two":[71],"practical":[72],"settings:":[73],"feedback-guided":[74],"repair,":[75],"where":[76,93,139],"using":[81],"buggy":[82],"marked":[84],"together":[86],"with":[87],"feedback,":[89],"reference-guided":[91],"restyling,":[92],"modify":[95],"match":[98],"target":[100],"chart":[101],"image.Evaluating":[102],"24":[103],"state-of-theart":[104],"VLMs":[105],"reveals":[106],"that":[107,155],"remains":[111],"challenging:":[112],"Claude":[113],"Opus":[114],"4.6":[115],"achieves":[116],"the":[117,176],"best":[118],"overall":[119,168],"pass":[120,169],"rate":[121,170],"76.0%,":[123],"while":[124],"most":[125],"open-source":[126],"remain":[128],"below":[129],"50%.Performance":[130],"particularly":[132],"weak":[133],"on":[134,164],"visually":[135],"style":[137],"adaptation,":[138],"Claude-4.6-Sonnetachieves":[140],"only":[141],"55.71%.To":[142],"establish":[143],"baseline,":[146],"we":[147],"further":[148],"propose":[149],"VisEd-itAgent,":[150],"render-grounded":[152,179],"framework":[154],"iteratively":[156],"generates,":[157],"executes,":[158],"validates,":[159],"refines":[161],"candidate":[162],"edits.Built":[163],"GPT-4o,":[165],"VisEditAgent":[166],"improves":[167],"55.75%":[172],"67.99%,":[174],"demonstrating":[175],"importance":[177],"for":[181],"faithful":[182],"editing.We":[184],"will":[185],"release":[186],"VisEdit-Bench":[187],"at":[188],"https://github.com/vis-nlp/":[189],"VisEditBench.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-08-13T00:00:00"}