{"id":"https://openalex.org/W4415539272","doi":"https://doi.org/10.1145/3746027.3755596","title":"Boosting Chart-to-Code Generation in MLLM via Dual Preference-Guided Refinement","display_name":"Boosting Chart-to-Code Generation in MLLM via Dual Preference-Guided Refinement","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539272","doi":"https://doi.org/10.1145/3746027.3755596"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3755596","doi":"https://doi.org/10.1145/3746027.3755596","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755596","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","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":"Proceedings of the 33rd ACM International Conference on Multimedia","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://doi.org/10.1145/3746027.3755596","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020823803","display_name":"Zhihan Zhang","orcid":"https://orcid.org/0009-0009-5813-9172","observed_orcids":["https://orcid.org/0009-0009-5813-9172"]},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhihan Zhang","raw_affiliation_strings":["Singapore Management University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0009-5813-9172","affiliations":[{"raw_affiliation_string":"Singapore Management University, Singapore, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023326846","display_name":"Yixin Cao","orcid":"https://orcid.org/0000-0001-7157-6961","observed_orcids":["https://orcid.org/0000-0001-7157-6961"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixin Cao","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7157-6961","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081165986","display_name":"Lizi Liao","orcid":"https://orcid.org/0000-0002-9973-3305","observed_orcids":["https://orcid.org/0000-0002-9973-3305"]},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lizi Liao","raw_affiliation_strings":["Singapore Management University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-9973-3305","affiliations":[{"raw_affiliation_string":"Singapore Management University, Singapore, Singapore","institution_ids":["https://openalex.org/I79891267"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6121,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.94633265,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"11032","last_page":"11041"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9779999852180481,"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":0.9779999852180481,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.004900000058114529,"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":0.004800000227987766,"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/multimodal-large-language-models","display_name":"multimodal large language models","score":0.9539999961853027},{"id":"https://openalex.org/keywords/offline-reinforcement-learning","display_name":"offline reinforcement learning","score":0.7160000205039978},{"id":"https://openalex.org/keywords/variant-generation","display_name":"variant generation","score":0.4959999918937683},{"id":"https://openalex.org/keywords/visual-fidelity","display_name":"visual fidelity","score":0.5370000004768372},{"id":"https://openalex.org/keywords/program-correctness","display_name":"program correctness","score":0.7160000205039978},{"id":"https://openalex.org/keywords/cross-modal-reasoning","display_name":"cross-modal reasoning","score":0.574999988079071}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8269000053405762},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.8026000261306763},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6022999882698059},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5598999857902527},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5339999794960022},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5199000239372253},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5097000002861023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.486299991607666},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.46059998869895935},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.447299987077713},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.4320000112056732},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.39750000834465027},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.37209999561309814},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3603000044822693},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3483999967575073},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3009999990463257},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2806999981403351},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C190812933","wikidata":"https://www.wikidata.org/wiki/Q28923","display_name":"Chart","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3746027.3755596","doi":"https://doi.org/10.1145/3746027.3755596","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755596","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","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":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.02906","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.02906","pdf_url":"https://arxiv.org/pdf/2504.02906","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":"pmh:oai:ink.library.smu.edu.sg:sis_research-11789","doi":null,"is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/10787","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1145/3746027.3755596","raw_type":"Conference Proceeding Article"},{"id":"doi:10.48550/arxiv.2504.02906","doi":"https://doi.org/10.48550/arxiv.2504.02906","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.02906","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:10.1145/3746027.3755596","doi":"https://doi.org/10.1145/3746027.3755596","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755596","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","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":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2453079827","display_name":null,"funder_award_id":"AcRF Tier 2","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G6854926366","display_name":null,"funder_award_id":"Tier 2","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415539272.pdf","grobid_xml":"https://content.openalex.org/works/W4415539272.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W4285255856","https://openalex.org/W4285292339","https://openalex.org/W4385570745","https://openalex.org/W4385571099","https://openalex.org/W4385572634","https://openalex.org/W4385573930","https://openalex.org/W4389156632","https://openalex.org/W4390041933","https://openalex.org/W4390871980","https://openalex.org/W4392011670","https://openalex.org/W4402670103","https://openalex.org/W4402670747","https://openalex.org/W4402670859","https://openalex.org/W4402683795","https://openalex.org/W4403853618","https://openalex.org/W4404389315","https://openalex.org/W4404783411","https://openalex.org/W4406489046","https://openalex.org/W4411113317","https://openalex.org/W4413144696","https://openalex.org/W4415123899","https://openalex.org/W4416035920","https://openalex.org/W6929303426","https://openalex.org/W7103755402"],"related_works":["https://openalex.org/W4415332936","https://openalex.org/W6929303426","https://openalex.org/W7108247839","https://openalex.org/W7172265321","https://openalex.org/W4415330511","https://openalex.org/W7158423277","https://openalex.org/W4412888781","https://openalex.org/W6910650539","https://openalex.org/W4399759273","https://openalex.org/W4416036265"],"abstract_inverted_index":{"Translating":[0],"chart":[1],"images":[2],"into":[3],"executable":[4],"plotting":[5,158],"scripts-referred":[6],"to":[7,18,63,108,132,155],"as":[8],"the":[9,42,134,147],"chart-to-code":[10],"generation":[11,101],"task-requires":[12],"Multimodal":[13],"Large":[14],"Language":[15],"Models":[16],"(MLLMs)":[17],"perform":[19],"fine-grained":[20],"visual":[21,44,54,105],"parsing,":[22],"precise":[23],"code":[24,38,51,159,171],"synthesis,":[25],"and":[26,46,53,66,103,118,165,172],"robust":[27],"cross-modal":[28],"reasoning.":[29],"However,":[30],"this":[31],"task":[32],"is":[33],"inherently":[34],"under-constrained:":[35],"multiple":[36],"valid":[37],"implementations":[39],"can":[40],"produce":[41,110],"same":[43],"chart,":[45],"evaluation":[47],"must":[48],"consider":[49],"both":[50],"correctness":[52],"fidelity":[55],"across":[56],"diverse":[57],"dimensions.":[58],"This":[59],"makes":[60],"it":[61],"difficult":[62],"learn":[64],"accurate":[65],"generalizable":[67],"mappings":[68],"through":[69],"standard":[70],"supervised":[71],"fine-tuning.":[72],"To":[73],"address":[74],"these":[75],"challenges,":[76],"we":[77],"propose":[78],"a":[79,86,98,104],"dual":[80],"preference-guided":[81],"refinement":[82],"framework":[83,144],"that":[84,142,160],"combines":[85],"feedback-driven,":[87],"dual-modality":[88],"reward":[89,106],"mechanism":[90],"with":[91],"iterative":[92],"preference":[93,113,115],"learning.":[94],"Our":[95],"approach":[96],"introduces":[97],"structured":[99],"variant":[100],"strategy":[102],"model":[107,135],"efficiently":[109],"high-quality,":[111],"aspect-aware":[112],"pairs-making":[114],"collection":[116],"scalable":[117],"supervision":[119],"more":[120],"targeted.":[121],"These":[122],"preferences":[123],"are":[124,174],"used":[125],"in":[126],"an":[127],"offline":[128],"reinforcement":[129],"learning":[130],"setup":[131],"optimize":[133],"toward":[136],"multi-dimensional":[137],"fidelity.":[138],"Experimental":[139],"results":[140],"show":[141],"our":[143],"significantly":[145],"enhances":[146],"performance":[148],"of":[149],"general-purpose":[150],"open-source":[151],"MLLMs,":[152],"enabling":[153],"them":[154],"generate":[156],"high-quality":[157],"rivals":[161],"specialized":[162],"chart-centric":[163],"models":[164],"even":[166],"some":[167],"proprietary":[168],"systems.":[169],"The":[170],"datasets":[173],"publicly":[175],"available":[176],"at":[177],"https://github.com/Zhihan72/Chart2Code.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-25T00:00:00"}