{"id":"https://openalex.org/W4414449236","doi":"https://doi.org/10.1145/3756681.3757003","title":"LLM Code Customization with Visual Results: A Benchmark on TikZ","display_name":"LLM Code Customization with Visual Results: A Benchmark on TikZ","publication_year":2025,"publication_date":"2025-06-17","ids":{"openalex":"https://openalex.org/W4414449236","doi":"https://doi.org/10.1145/3756681.3757003"},"language":"en","primary_location":{"id":"doi:10.1145/3756681.3757003","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3756681.3757003","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 29th International Conference on Evaluation and Assessment in Software Engineering","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3756681.3757003","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Charly Reux","orcid":"https://orcid.org/0009-0008-8708-8362"},"institutions":[{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I28221208","display_name":"Institut National des Sciences Appliqu\u00e9es de Rennes","ror":"https://ror.org/04xaa4j22","country_code":"FR","type":"education","lineage":["https://openalex.org/I28221208"]},{"id":"https://openalex.org/I3124938446","display_name":"Universit\u00e9 Rennes 2","ror":"https://ror.org/01m84wm78","country_code":"FR","type":"education","lineage":["https://openalex.org/I3124938446"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Charly Reux","raw_affiliation_strings":["Univ Rennes, Rennes, France; DiverSE, Inria, Rennes, France; IRISA, Rennes, France and INSA, Rennes, France","DiverSe - Diversity-centric Software Engineering (Campus de Beaulieu, 35042 Rennes cedex - France)"],"raw_orcid":"https://orcid.org/0009-0008-8708-8362","affiliations":[{"raw_affiliation_string":"Univ Rennes, Rennes, France; DiverSE, Inria, Rennes, France; IRISA, Rennes, France and INSA, Rennes, France","institution_ids":["https://openalex.org/I56067802","https://openalex.org/I3124938446","https://openalex.org/I28221208","https://openalex.org/I2802519937"]},{"raw_affiliation_string":"DiverSe - Diversity-centric Software Engineering (Campus de Beaulieu, 35042 Rennes cedex - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003973216","display_name":"Mathieu Acher","orcid":"https://orcid.org/0000-0003-1483-3858"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I28221208","display_name":"Institut National des Sciences Appliqu\u00e9es de Rennes","ror":"https://ror.org/04xaa4j22","country_code":"FR","type":"education","lineage":["https://openalex.org/I28221208"]},{"id":"https://openalex.org/I3124938446","display_name":"Universit\u00e9 Rennes 2","ror":"https://ror.org/01m84wm78","country_code":"FR","type":"education","lineage":["https://openalex.org/I3124938446"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mathieu Acher","raw_affiliation_strings":["Univ Rennes, Rennes, France; Inria, Rennes, France; CNRS, Rennes, France and INSA, Rennes, France","DiverSe - Diversity-centric Software Engineering (Campus de Beaulieu, 35042 Rennes cedex - France)"],"raw_orcid":"https://orcid.org/0000-0003-1483-3858","affiliations":[{"raw_affiliation_string":"Univ Rennes, Rennes, France; Inria, Rennes, France; CNRS, Rennes, France and INSA, Rennes, France","institution_ids":["https://openalex.org/I28221208","https://openalex.org/I56067802","https://openalex.org/I3124938446","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"DiverSe - Diversity-centric Software Engineering (Campus de Beaulieu, 35042 Rennes cedex - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103021471","display_name":"Djamel Eddine Khelladi","orcid":"https://orcid.org/0000-0002-2218-650X"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I3124938446","display_name":"Universit\u00e9 Rennes 2","ror":"https://ror.org/01m84wm78","country_code":"FR","type":"education","lineage":["https://openalex.org/I3124938446"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Djamel Eddine Khelladi","raw_affiliation_strings":["Univ Rennes, Rennes, France; Inria, Rennes, France; CNRS, Rennes, France and IRISA, Rennes, France","DiverSe - Diversity-centric Software Engineering (Campus de Beaulieu, 35042 Rennes cedex - France)"],"raw_orcid":"https://orcid.org/0000-0002-2218-650X","affiliations":[{"raw_affiliation_string":"Univ Rennes, Rennes, France; Inria, Rennes, France; CNRS, Rennes, France and IRISA, Rennes, France","institution_ids":["https://openalex.org/I2802519937","https://openalex.org/I56067802","https://openalex.org/I3124938446","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"DiverSe - Diversity-centric Software Engineering (Campus de Beaulieu, 35042 Rennes cedex - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012148559","display_name":"Cl\u00e9ment Quinton","orcid":"https://orcid.org/0000-0003-3203-6107"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Cl\u00e9ment Quinton","raw_affiliation_strings":["Univ. Lille, Lille, France; CNRS, Lille, France and Inria, Lille, France","DiverSe - Diversity-centric Software Engineering (Campus de Beaulieu, 35042 Rennes cedex - France)"],"raw_orcid":"https://orcid.org/0000-0003-3203-6107","affiliations":[{"raw_affiliation_string":"Univ. Lille, Lille, France; CNRS, Lille, France and Inria, Lille, France","institution_ids":["https://openalex.org/I2279609970","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"DiverSe - Diversity-centric Software Engineering (Campus de Beaulieu, 35042 Rennes cedex - France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002785466","display_name":"Olivier Barais","orcid":"https://orcid.org/0000-0002-4551-8562"},"institutions":[{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]},{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I3124938446","display_name":"Universit\u00e9 Rennes 2","ror":"https://ror.org/01m84wm78","country_code":"FR","type":"education","lineage":["https://openalex.org/I3124938446"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Olivier Barais","raw_affiliation_strings":["Univ. Rennes, Rennes, France; IRISA, Rennes, France and Inria, Rennes, France","SPIRALS - Self-adaptation for distributed services and large software systems (Centre Inria de l'Universit\u00e9 de Lille ,170 Av. de Bretagne, 59000 Lille - France)"],"raw_orcid":"https://orcid.org/0000-0002-4551-8562","affiliations":[{"raw_affiliation_string":"Univ. Rennes, Rennes, France; IRISA, Rennes, France and Inria, Rennes, France","institution_ids":["https://openalex.org/I2802519937","https://openalex.org/I56067802","https://openalex.org/I3124938446"]},{"raw_affiliation_string":"SPIRALS - Self-adaptation for distributed services and large software systems (Centre Inria de l'Universit\u00e9 de Lille ,170 Av. de Bretagne, 59000 Lille - France)","institution_ids":["https://openalex.org/I2279609970"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3589,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91295455,"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":"1086","last_page":"1096"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13999","display_name":"Digital Rights Management and Security","score":0.9699000120162964,"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"}},"topics":[{"id":"https://openalex.org/T13999","display_name":"Digital Rights Management and Security","score":0.9699000120162964,"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/personalization","display_name":"Personalization","score":0.7616999745368958},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.7361999750137329},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7246999740600586},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.429500013589859},{"id":"https://openalex.org/keywords/codebase","display_name":"Codebase","score":0.41110000014305115},{"id":"https://openalex.org/keywords/visual-programming-language","display_name":"Visual programming language","score":0.4083999991416931},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.3961000144481659}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.795199990272522},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.7616999745368958},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.7361999750137329},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7246999740600586},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.429500013589859},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4115999937057495},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.41110000014305115},{"id":"https://openalex.org/C128644962","wikidata":"https://www.wikidata.org/wiki/Q683111","display_name":"Visual programming language","level":2,"score":0.4083999991416931},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.39660000801086426},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.3961000144481659},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.39570000767707825},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.39419999718666077},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.3725999891757965},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34369999170303345},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.29440000653266907},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.27059999108314514},{"id":"https://openalex.org/C2777055276","wikidata":"https://www.wikidata.org/wiki/Q7936580","display_name":"Visual approach","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25529998540878296}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3756681.3757003","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3756681.3757003","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 29th International Conference on Evaluation and Assessment in Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.04670","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.04670","pdf_url":"https://arxiv.org/pdf/2505.04670","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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:HAL:hal-05049250v2","is_oa":true,"landing_page_url":"https://hal.science/hal-05049250","pdf_url":"https://hal.science/hal-05049250v2/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"EASE'25 - Evaluation and Assessment in Software Engineering, Jun 2025, Istanbul, Turkey. pp.1-10, &#x27E8;10.1145/3756681.3757003&#x27E9;","raw_type":"Conference papers"}],"best_oa_location":{"id":"doi:10.1145/3756681.3757003","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3756681.3757003","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 29th International Conference on Evaluation and Assessment in Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,32,62,75,81],"rise":[2],"of":[3,11,83,99],"AI-based":[4],"code":[5,9,52,58,90,132,144,164],"generation,":[6],"customizing":[7],"existing":[8,126],"out":[10],"natural":[12],"language":[13],"instructions":[14],"to":[15,30,79,88,116,129,162],"modify":[16,131],"visual":[17,94,114,136,159],"results":[18],"\u2013":[19,25],"such":[20],"as":[21,47],"figures":[22],"or":[23],"images":[24],"has":[26],"become":[27],"possible,":[28],"promising":[29],"reduce":[31],"need":[33],"for":[34,155],"deep":[35],"programming":[36],"expertise.":[37],"However,":[38],"even":[39],"experienced":[40],"developers":[41],"can":[42],"struggle":[43,128],"with":[44,66,121,135,158],"this":[45,70],"task,":[46],"it":[48],"requires":[49],"identifying":[50],"relevant":[51],"regions":[53],"(feature":[54],"location),":[55],"generating":[56],"valid":[57],"variants,":[59],"and":[60,108,179],"ensuring":[61],"modifications":[63],"reliably":[64,130],"align":[65],"user":[67],"intent.":[68],"In":[69],"paper,":[71],"we":[72],"introduce":[73],"vTikZ,":[74],"first":[76],"benchmark":[77,97],"designed":[78],"evaluate":[80],"ability":[82],"Large":[84],"Language":[85],"Models":[86],"(LLMs)":[87],"customize":[89],"while":[91],"preserving":[92],"coherent":[93],"outcomes.":[95],"Our":[96],"consists":[98],"carefully":[100],"curated":[101],"vTikZ":[102,150],"editing":[103,145],"scenarios,":[104],"parameterized":[105],"ground":[106],"truths,":[107],"a":[109,139],"reviewing":[110],"tool":[111],"that":[112,125,149],"leverages":[113],"feedback":[115,160],"assess":[117],"correctness.":[118],"Empirical":[119],"evaluation":[120],"state-of-the-art":[122],"LLMs":[123,157],"shows":[124],"solutions":[127],"in":[133,141,167],"alignment":[134],"intent,":[137],"highlighting":[138],"gap":[140],"current":[142],"AI-assisted":[143],"approaches.":[146],"We":[147],"argue":[148],"opens":[151],"new":[152],"research":[153],"directions":[154],"integrating":[156],"mechanisms":[161],"improve":[163],"customization":[165],"tasks":[166],"various":[168],"domains":[169],"beyond":[170],"TikZ,":[171],"including":[172],"image":[173],"processing,":[174],"art":[175],"creation,":[176],"Web":[177],"design,":[178],"3D":[180],"modeling.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
