{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T15:55:56Z","timestamp":1766159756157,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755862","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:38:54Z","timestamp":1761377934000},"page":"9053-9061","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Closing the Feedback Loop in Text2Vis: Refining Visualization with Vision-Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2945-6170","authenticated-orcid":false,"given":"Shengze","family":"Shi","sequence":"first","affiliation":[{"name":"State Key Laboratory of Intelligent Game, Institute of Software Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0408-9447","authenticated-orcid":false,"given":"Tao","family":"Ren","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Intelligent Game, Institute of Software Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5235-1549","authenticated-orcid":false,"given":"Guoliang","family":"Zhu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Intelligent Game, Institute of Software Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0728-6236","authenticated-orcid":false,"given":"Guandong","family":"Feng","sequence":"additional","affiliation":[{"name":"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"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1530-7499","authenticated-orcid":false,"given":"Jun","family":"Hu","sequence":"additional","affiliation":[{"name":"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"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3495883"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.62"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681167"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3641904"},{"key":"e_1_3_2_1_5_1","first-page":"906","volume-title":"IEEE TVCG","volume":"26","author":"Cui Weiwei","year":"2019","unstructured":"Weiwei Cui, Xiaoyu Zhang, Yun Wang, et al., 2019. Text-to-viz: Automatic generation of infographics from proportion-related natural language statements. IEEE TVCG, Vol. 26, 1 (2019), 906-916."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00128"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807442.2807478"},{"key":"e_1_3_2_1_8_1","volume-title":"Raj Sanjay Shah, Hanspeter Pfister, and Sashank Varma.","author":"Guo Grace","year":"2024","unstructured":"Grace Guo, Jenna Jiayi Kang, Raj Sanjay Shah, Hanspeter Pfister, and Sashank Varma. 2024. Understanding Graphical Perception in Data Visualization through Zero-shot Prompting of Vision-Language Models. arXiv preprint arXiv:2411.00257 (2024)."},{"key":"e_1_3_2_1_9_1","first-page":"309","volume-title":"IEEE TVCG","volume":"24","author":"Hoque Enamul","year":"2017","unstructured":"Enamul Hoque, Vidya Setlur, Melanie Tory, and Isaac Dykeman. 2017. Applying pragmatics principles for interaction with visual analytics. IEEE TVCG, Vol. 24, 1 (2017), 309-318."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680790"},{"key":"e_1_3_2_1_11_1","volume-title":"Guard: Role-playing to generate natural-language jailbreakings to test guideline adherence of large language models. arXiv preprint arXiv:2402.03299","author":"Jin Haibo","year":"2024","unstructured":"Haibo Jin, Ruoxi Chen, Andy Zhou, Yang Zhang, and Haohan Wang. 2024. Guard: Role-playing to generate natural-language jailbreakings to test guideline adherence of large language models. arXiv preprint arXiv:2402.03299 (2024)."},{"key":"e_1_3_2_1_12_1","volume-title":"Prompt4Vis: Prompting large language models with example mining and schema filtering for tabular data visualization. arXiv preprint arXiv:2402.07909","author":"Li Shuaimin","year":"2024","unstructured":"Shuaimin Li, Xuanang Chen, Yuanfeng Song, Yunze Song, and Chen Zhang. 2024. Prompt4Vis: Prompting large language models with example mining and schema filtering for tabular data visualization. arXiv preprint arXiv:2402.07909 (2024)."},{"key":"e_1_3_2_1_13_1","volume-title":"nvBench: A large-scale synthesized dataset for cross-domain natural language to visualization task. arXiv preprint arXiv:2112.12926","author":"Luo Yuyu","year":"2021","unstructured":"Yuyu Luo, Jiawei Tang, and Guoliang Li. 2021a. nvBench: A large-scale synthesized dataset for cross-domain natural language to visualization task. arXiv preprint arXiv:2112.12926 (2021)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457261"},{"key":"e_1_3_2_1_15_1","first-page":"217","volume-title":"IEEE TVCG","volume":"28","author":"Luo Yuyu","year":"2021","unstructured":"Yuyu Luo, Nan Tang, Guoliang Li, Jiawei Tang, Chengliang Chai, and Xuedi Qin. 2021c. Natural language to visualization by neural machine translation. IEEE TVCG, Vol. 28, 1 (2021), 217-226."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3274199"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.906"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.31219\/osf.io\/3eg9c"},{"key":"e_1_3_2_1_19_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Olausson Theo X","year":"2023","unstructured":"Theo X Olausson, Jeevana Priya Inala, Chenglong Wang, Jianfeng Gao, and Armando Solar-Lezama. 2023. Is Self-Repair a Silver Bullet for Code Generation?. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_20_1","volume-title":"Machine learning for visualization recommendation systems: Open challenges and future directions. arXiv preprint arXiv:2302.00569","author":"Podo Luca","year":"2023","unstructured":"Luca Podo, Bardh Prenkaj, and Paola Velardi. 2023. Machine learning for visualization recommendation systems: Open challenges and future directions. arXiv preprint arXiv:2302.00569 (2023)."},{"key":"e_1_3_2_1_21_1","volume-title":"Jing Xu, Maryam Fazel-Zarandi, Mohit Bansal, Sainbayar Sukhbaatar, Jason Weston, and Jane Yu.","author":"Prasad Archiki","year":"2024","unstructured":"Archiki Prasad, Weizhe Yuan, Richard Yuanzhe Pang, Jing Xu, Maryam Fazel-Zarandi, Mohit Bansal, Sainbayar Sukhbaatar, Jason Weston, and Jane Yu. 2024. Self-Consistency Preference Optimization. arXiv preprint arXiv:2411.04109 (2024)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539330"},{"key":"e_1_3_2_1_23_1","first-page":"672","article-title":"Are we closing the loop yet? gaps in the generalizability of vis4ml research","volume":"30","author":"Subramonyam Hariharan","year":"2023","unstructured":"Hariharan Subramonyam and Jessica Hullman. 2023. Are we closing the loop yet? gaps in the generalizability of vis4ml research. IEEE Transactions on Visualization and Computer Graphics, Vol. 30, 1 (2023), 672-682.","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"e_1_3_2_1_24_1","volume-title":"Chartgpt: Leveraging llms to generate charts from abstract natural language","author":"Tian Yuan","year":"2024","unstructured":"Yuan Tian, Weiwei Cui, Dazhen Deng, et al., 2024. Chartgpt: Leveraging llms to generate charts from abstract natural language. IEEE TVCG (2024)."},{"key":"e_1_3_2_1_25_1","volume-title":"Two tales of persona in llms: A survey of role-playing and personalization. arXiv preprint arXiv:2406.01171","author":"Tseng Yu-Min","year":"2024","unstructured":"Yu-Min Tseng, Yu-Chao Huang, Teng-Yun Hsiao, Wei-Lin Chen, Chao-Wei Huang, Yu Meng, and Yun-Nung Chen. 2024. Two tales of persona in llms: A survey of role-playing and personalization. arXiv preprint arXiv:2406.01171 (2024)."},{"key":"e_1_3_2_1_26_1","volume-title":"Aakanksha Chowdhery, and Denny Zhou.","author":"Wang Xuezhi","year":"2022","unstructured":"Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022. Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171 (2022)."},{"key":"e_1_3_2_1_27_1","volume-title":"Rolellm: Benchmarking, eliciting, and enhancing role-playing abilities of large language models. arXiv preprint arXiv:2310.00746","author":"Wang Zekun Moore","year":"2023","unstructured":"Zekun Moore Wang, Zhongyuan Peng, Haoran Que, et al., 2023. Rolellm: Benchmarking, eliciting, and enhancing role-playing abilities of large language models. arXiv preprint arXiv:2310.00746 (2023)."},{"key":"e_1_3_2_1_28_1","unstructured":"Jason Wei Yi Tay Rishi Bommasani et al. 2022. Emergent abilities of large language models. arXiv:2206.07682 (2022)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3654992"},{"key":"e_1_3_2_1_30_1","unstructured":"Peng Xia Siwei Han Shi Qiu Yiyang Zhou Zhaoyang Wang Wenhao Zheng Zhaorun Chen Chenhang Cui Mingyu Ding Linjie Li Lijuan Wang and Huaxiu Yao. 2025. MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=HnhNRrLPwm"},{"key":"e_1_3_2_1_31_1","unstructured":"Renqiu Xia Bo Zhang Hancheng Ye Xiangchao Yan Qi Liu Hongbin Zhou Zijun Chen Peng Ye Min Dou Botian Shi et al. 2024. Chartx & chartvlm: A versatile benchmark and foundation model for complicated chart reasoning. arXiv preprint arXiv:2402.12185 (2024)."},{"key":"e_1_3_2_1_32_1","unstructured":"Yilin Ye Jianing Hao Yihan Hou et al. 2024. Generative ai for visualization: State of the art and future directions. Visual Informatics (2024)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"e_1_3_2_1_34_1","volume-title":"A systematic literature review on large language models for automated program repair. arXiv preprint arXiv:2405.01466","author":"Zhang Quanjun","year":"2024","unstructured":"Quanjun Zhang, Chunrong Fang, Yang Xie, YuXiang Ma, Weisong Sun, Yun Yang, and Zhenyu Chen. 2024a. A systematic literature review on large language models for automated program repair. arXiv preprint arXiv:2405.01466 (2024)."},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the 32nd ACM International Conference on Multimedia. 3897-3906","author":"Zhao Bowen","year":"2024","unstructured":"Bowen Zhao, Tianhao Cheng, Yuejie Zhang, Ying Cheng, Rui Feng, and Xiaobo Zhang. 2024. CT2C-QA: Multimodal Question Answering over Chinese Text, Table and Chart. In Proceedings of the 32nd ACM International Conference on Multimedia. 3897-3906."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755862","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:11:55Z","timestamp":1765339915000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755862"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":35,"alternative-id":["10.1145\/3746027.3755862","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755862","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}