{"id":"https://openalex.org/W4411113317","doi":"https://doi.org/10.18653/v1/2025.findings-naacl.164","title":"Plot2Code: A Comprehensive Benchmark for Evaluating Multi-modal Large Language Models in Code Generation from Scientific Plots","display_name":"Plot2Code: A Comprehensive Benchmark for Evaluating Multi-modal Large Language Models in Code Generation from Scientific Plots","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411113317","doi":"https://doi.org/10.18653/v1/2025.findings-naacl.164"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-naacl.164","doi":"https://doi.org/10.18653/v1/2025.findings-naacl.164","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-naacl.164","pdf_url":"https://aclanthology.org/2025.findings-naacl.164.pdf","source":{"id":"https://openalex.org/S4363605604","display_name":"Findings of the Association for Computational Linguistics: NAACL","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":"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: NAACL 2025","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2025.findings-naacl.164.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012404343","display_name":"Chengyue Wu","orcid":"https://orcid.org/0000-0002-3789-404X","observed_orcids":["https://orcid.org/0000-0002-3789-404X"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Chengyue Wu","raw_affiliation_strings":["ARC Lab , Tencent PCG","The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ARC Lab , Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138920332","display_name":"Zhixuan Liang","orcid":"https://orcid.org/0009-0008-1609-7712","observed_orcids":["https://orcid.org/0009-0008-1609-7712"]},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhixuan Liang","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047802386","display_name":"Yixiao Ge","orcid":"https://orcid.org/0000-0002-5351-5329","observed_orcids":["https://orcid.org/0000-0002-5351-5329"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixiao Ge","raw_affiliation_strings":["ARC Lab , Tencent PCG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ARC Lab , Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064714359","display_name":"Qiushan Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qiushan Guo","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011396755","display_name":"Zeyu Lu","orcid":"https://orcid.org/0000-0002-4272-8388","observed_orcids":["https://orcid.org/0000-0002-4272-8388"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyu Lu","raw_affiliation_strings":["Shanghai Jiao Tong University https ://github.com/ TencentARC/Plot2Code"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University https ://github.com/ TencentARC/Plot2Code","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329217","display_name":"Jiahao Wang","orcid":"https://orcid.org/0009-0009-9227-2794","observed_orcids":["https://orcid.org/0009-0009-9227-2794","https://orcid.org/0009-0000-2100-827X"]},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiahao Wang","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102004349","display_name":"Ying Shan","orcid":"https://orcid.org/0000-0001-7673-8325","observed_orcids":["https://orcid.org/0000-0001-7673-8325"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Shan","raw_affiliation_strings":["ARC Lab , Tencent PCG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ARC Lab , Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100752685","display_name":"Ping Luo","orcid":"https://orcid.org/0000-0002-6645-4721","observed_orcids":["https://orcid.org/0000-0002-6645-4721","https://orcid.org/0000-0002-0039-747X"]},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ping Luo","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":24.9232,"has_fulltext":true,"cited_by_count":75,"citation_normalized_percentile":{"value":0.99525913,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3006","last_page":"3028"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9911999702453613,"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":0.9911999702453613,"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/T10260","display_name":"Software Engineering Research","score":0.004600000102072954,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.00139999995008111,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.9539999961853027},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.5490000247955322},{"id":"https://openalex.org/keywords/plotly","display_name":"Plotly","score":0.7129999995231628},{"id":"https://openalex.org/keywords/gpt-4v","display_name":"GPT-4V","score":0.8140000104904175},{"id":"https://openalex.org/keywords/visual-coding","display_name":"visual coding","score":0.4560000002384186}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7973862886428833},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.63995361328125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6383697986602783},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5700384974479675},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4149426221847534},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.09078776836395264},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07505419850349426},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.findings-naacl.164","doi":"https://doi.org/10.18653/v1/2025.findings-naacl.164","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-naacl.164","pdf_url":"https://aclanthology.org/2025.findings-naacl.164.pdf","source":{"id":"https://openalex.org/S4363605604","display_name":"Findings of the Association for Computational Linguistics: NAACL","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":"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: NAACL 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2405.07990","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.07990","pdf_url":"https://arxiv.org/pdf/2405.07990","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2405.07990","doi":"https://doi.org/10.48550/arxiv.2405.07990","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2405.07990","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-naacl.164","doi":"https://doi.org/10.18653/v1/2025.findings-naacl.164","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-naacl.164","pdf_url":"https://aclanthology.org/2025.findings-naacl.164.pdf","source":{"id":"https://openalex.org/S4363605604","display_name":"Findings of the Association for Computational Linguistics: NAACL","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":"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: NAACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411113317.pdf","grobid_xml":"https://content.openalex.org/works/W4411113317.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W3001279689","https://openalex.org/W3177813494","https://openalex.org/W3195140297","https://openalex.org/W4285255856","https://openalex.org/W4376167329","https://openalex.org/W4384918448","https://openalex.org/W4385473806","https://openalex.org/W4385570088","https://openalex.org/W4386185625","https://openalex.org/W4386908092","https://openalex.org/W4387561528","https://openalex.org/W4387723654","https://openalex.org/W4389217168","https://openalex.org/W4389708725","https://openalex.org/W4390041269","https://openalex.org/W4390041933","https://openalex.org/W4390690464","https://openalex.org/W4390723197","https://openalex.org/W4391272793","https://openalex.org/W4392678661","https://openalex.org/W4392822465","https://openalex.org/W4395065892","https://openalex.org/W4395098128","https://openalex.org/W4402672077","https://openalex.org/W4402683795","https://openalex.org/W4402713111","https://openalex.org/W4404783273","https://openalex.org/W4411120254","https://openalex.org/W4416707474","https://openalex.org/W7133225605"],"related_works":["https://openalex.org/W7220910559","https://openalex.org/W7125352929","https://openalex.org/W4399759273","https://openalex.org/W7161295972","https://openalex.org/W4407719597","https://openalex.org/W4415539272","https://openalex.org/W6910650539","https://openalex.org/W7164887291","https://openalex.org/W4416035208","https://openalex.org/W4404783273"],"abstract_inverted_index":{"Multi-modal":[0],"Large":[1],"Language":[2],"Models":[3],"have":[4],"shown":[5],"remarkable":[6],"progress":[7],"in":[8,138,177],"visual":[9,16,35,178],"contexts,":[10],"yet":[11],"their":[12],"ability":[13],"to":[14,32],"convert":[15],"figures":[17],"into":[18],"executable":[19],"code":[20,72,105],"remains":[21],"underexplored.To":[22],"address":[23],"this,":[24],"we":[25,86],"introduce":[26],"Plot2Code,":[27],"a":[28,74,126],"comprehensive":[29],"benchmark":[30],"designed":[31],"assess":[33,100],"MLLMs'":[34],"coding":[36],"capabilities.Plot2Code":[37],"includes":[38],"132":[39],"high-quality":[40],"matplotlib":[41],"plots":[42,55],"across":[43,83,129],"six":[44],"plot":[45,66],"types,":[46],"as":[47,49,115],"well":[48,118],"an":[50],"additional":[51],"150":[52],"and":[53,58,73,96,106,171],"86":[54],"from":[56,143],"Python's":[57],"R's":[59],"plotly":[60],"libraries":[61],"respectively,":[62],"totaling":[63],"368":[64],"plots.Each":[65],"is":[67],"paired":[68],"with":[69,119],"its":[70],"source":[71],"descriptive":[75],"instruction":[76],"generated":[77,104],"by":[78],"GPT-4,":[79],"enabling":[80],"thorough":[81],"evaluation":[82,90,164],"diverse":[84],"inputs.Furthermore,":[85],"propose":[87],"three":[88],"automatic":[89],"metrics-code":[91],"pass":[92],"rate,":[93],"text-match":[94],"ratio,":[95],"GPT-4V":[97,110],"rating":[98,111],"judgement-to":[99],"the":[101,109,144],"quality":[102],"of":[103,125,165,198],"rendered":[107,151],"images.Notably,":[108],"demonstrates":[112],"strong":[113],"reliability,":[114],"it":[116],"correlates":[117],"human":[120],"evaluations,":[121],"particularly":[122,180],"for":[123,161,181],"datasets":[124],"certain":[127],"size.Crossvalidation":[128],"MLLMs":[130,185],"(GPT-4V,":[131],"Gemini-1.5-Pro,and":[132],"Claude-3-Opus)":[133],"also":[134],"shows":[135],"high":[136],"consistency":[137],"ratings,":[139],"which":[140],"likely":[141],"stems":[142],"fact":[145],"that":[146],"ratings":[147],"are":[148],"based":[149],"on":[150,188],"images":[152],"rather":[153],"than":[154],"direct":[155],"MLLM":[156],"outputs,":[157],"indicating":[158],"minimal":[159],"bias":[160],"this":[162],"metric.Our":[163],"14":[166],"MLLMs,":[167],"including":[168],"both":[169],"proprietary,":[170],"open-source":[172],"models,":[173],"highlights":[174],"significant":[175],"challenges":[176],"coding,":[179],"textdense":[182],"plots,":[183],"where":[184],"heavily":[186],"rely":[187],"textual":[189],"instructions.We":[190],"believe":[191],"these":[192],"findings":[193],"will":[194],"advance":[195],"future":[196],"development":[197],"MLLMs.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":30},{"year":2025,"cited_by_count":39},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}