{"id":"https://openalex.org/W4415538918","doi":"https://doi.org/10.1145/3746027.3755862","title":"Closing the Feedback Loop in Text2Vis: Refining Visualization with Vision-Language Models","display_name":"Closing the Feedback Loop in Text2Vis: Refining Visualization with Vision-Language Models","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538918","doi":"https://doi.org/10.1145/3746027.3755862"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755862","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755862","pdf_url":null,"source":null,"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"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755862","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111063800","display_name":"Shengze Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shengze Shi","raw_affiliation_strings":["State Key Laboratory of Intelligent Game, Institute of Software Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-2945-6170","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Game, Institute of Software Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019680908","display_name":"Tao Ren","orcid":"https://orcid.org/0000-0003-0408-9447"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Ren","raw_affiliation_strings":["State Key Laboratory of Intelligent Game, Institute of Software Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0408-9447","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Game, Institute of Software Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062633151","display_name":"Guoliang Zhu","orcid":"https://orcid.org/0009-0007-5235-1549"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoliang Zhu","raw_affiliation_strings":["State Key Laboratory of Intelligent Game, Institute of Software Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-5235-1549","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Game, Institute of Software Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101260230","display_name":"Guandong Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guandong Feng","raw_affiliation_strings":["State Key Laboratory of Intelligent Game, Institute of Software Chinese Academy of Sciences, Beijing, China and University of the Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-0728-6236","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Game, Institute of Software Chinese Academy of Sciences, Beijing, China and University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100405540","display_name":"Jun Hu","orcid":"https://orcid.org/0009-0005-1530-7499"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Hu","raw_affiliation_strings":["State Key Laboratory of Intelligent Game, Institute of Software Chinese Academy of Sciences, Beijing, China and University of the Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-1530-7499","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Game, Institute of Software Chinese Academy of Sciences, Beijing, China and University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5111063800"],"corresponding_institution_ids":["https://openalex.org/I4210128818"],"apc_list":null,"apc_paid":null,"fwci":2.1733,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.90958059,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"9053","last_page":"9061"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9919000267982483,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9919000267982483,"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/T10260","display_name":"Software Engineering Research","score":0.9871000051498413,"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/T10028","display_name":"Topic Modeling","score":0.9778000116348267,"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/visualization","display_name":"Visualization","score":0.8533999919891357},{"id":"https://openalex.org/keywords/data-visualization","display_name":"Data visualization","score":0.5412999987602234},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5026999711990356},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4205999970436096},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4097000062465668},{"id":"https://openalex.org/keywords/closing","display_name":"Closing (real estate)","score":0.39100000262260437},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.35030001401901245}],"concepts":[{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.8533999919891357},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8370000123977661},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.5412999987602234},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5026999711990356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4618000090122223},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4205999970436096},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4097000062465668},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3961000144481659},{"id":"https://openalex.org/C2778775528","wikidata":"https://www.wikidata.org/wiki/Q5135432","display_name":"Closing (real estate)","level":2,"score":0.39100000262260437},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3896999955177307},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.35030001401901245},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C14669888","wikidata":"https://www.wikidata.org/wiki/Q4014850","display_name":"Creative visualization","level":3,"score":0.33340001106262207},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.319599986076355},{"id":"https://openalex.org/C185578843","wikidata":"https://www.wikidata.org/wiki/Q10609775","display_name":"Information visualization","level":3,"score":0.3028999865055084},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2858999967575073},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.2694999873638153},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.25929999351501465}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755862","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755862","pdf_url":null,"source":null,"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"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755862","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755862","pdf_url":null,"source":null,"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W4382498938","https://openalex.org/W4384345745","https://openalex.org/W4389523846","https://openalex.org/W4392172801","https://openalex.org/W4396833645","https://openalex.org/W4401043400","https://openalex.org/W4403792079"],"related_works":[],"abstract_inverted_index":{"Text-to-Visualization":[0],"(Text2Vis)":[1],"generates":[2],"data":[3,13],"visualizations":[4],"directly":[5],"from":[6],"natural":[7],"language":[8,37],"queries,":[9],"democratizing":[10],"access":[11],"to":[12,28,83,124,139],"insights.":[14],"Early":[15],"Text2Vis":[16,85,113],"efforts,":[17],"primarily":[18],"relying":[19],"on":[20,54,79],"rule-based":[21],"systems":[22],"and":[23,65,101,115,134,143,159,161],"machine":[24],"learning":[25],"models,":[26],"struggled":[27],"handle":[29],"semantically":[30],"intricate":[31],"queries.":[32],"The":[33],"advent":[34],"of":[35,63],"large":[36],"models":[38,81],"(LLMs)":[39],"allows":[40],"for":[41],"better":[42],"generalization":[43],"in":[44],"generating":[45],"visualization":[46,93,141],"code.":[47],"However,":[48],"LLM-based":[49,158],"approaches":[50],"have":[51],"mainly":[52],"focused":[53],"textual":[55],"or":[56],"code-level":[57,145],"optimizations,":[58],"neglecting":[59],"the":[60],"potential":[61],"benefits":[62],"assessing":[64],"improving":[66],"visualized":[67],"charts.":[68],"Hence,":[69],"we":[70],"propose":[71],"Visualization":[72],"Refinement":[73],"(VisRef),":[74],"a":[75,97,126,129],"novel":[76],"framework":[77,105],"based":[78],"vision-language":[80],"(VLMs)":[82],"enhance":[84],"outputs.":[86],"(1)":[87],"Knowledge":[88],"Extraction":[89],"--":[90,119],"VisRef":[91,152],"extracts":[92],"assessment":[94,104],"knowledge":[95,121],"through":[96,128],"hierarchical":[98],"contrastive":[99],"prompt":[100],"multi-granularity":[102],"quality":[103,142],"by":[106],"comparing":[107],"superior":[108],"ground-truth":[109],"charts":[110],"with":[111,166],"inferior":[112],"outputs;":[114],"(2)":[116],"VLM":[117,127],"Fine-Tuning":[118],"This":[120],"is":[122],"used":[123],"fine-tune":[125],"two-stage":[130],"approach,":[131],"including":[132,157],"warm-up":[133],"iterative":[135],"preference":[136],"alignment":[137],"phases,":[138],"judge":[140],"provide":[144],"refinement":[146],"suggestions.":[147],"Experimental":[148],"results":[149],"demonstrate":[150],"that":[151],"significantly":[153],"outperforms":[154],"state-of-the-art":[155],"approaches,":[156],"VLM-prompted,":[160],"exhibits":[162],"strong":[163],"orthogonal":[164],"compatibility":[165],"existing":[167],"approaches.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-25T00:00:00"}
