{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T08:00:19Z","timestamp":1776931219490,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":80,"publisher":"ACM","funder":[{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LD25F020003"],"award-info":[{"award-number":["LD25F020003"]}]},{"name":"NSFC","award":["62421003"],"award-info":[{"award-number":["62421003"]}]},{"name":"NSFC","award":["62402428"],"award-info":[{"award-number":["62402428"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3772318.3790721","type":"proceedings-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T04:12:33Z","timestamp":1776053553000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Making Multimodal LLMs Reliable Chart Data Extractors: A Benchmark and Training Framework"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1035-4347","authenticated-orcid":false,"given":"Yuchen","family":"He","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2494-8131","authenticated-orcid":false,"given":"Peizhi","family":"Ying","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8868-5101","authenticated-orcid":false,"given":"Liqi","family":"Cheng","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0945-3989","authenticated-orcid":false,"given":"Kuilin","family":"Peng","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology, Guangzhou, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6089-7694","authenticated-orcid":false,"given":"Yuan","family":"Tian","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9057-8353","authenticated-orcid":false,"given":"Dazhen","family":"Deng","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1119-3237","authenticated-orcid":false,"given":"Yingcai","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,13]]},"reference":[{"key":"e_1_3_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.828"},{"key":"e_1_3_3_3_3_2","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang et\u00a0al. 2025. Qwen2.5-VL Technical Report. arxiv:https:\/\/arXiv.org\/abs\/2502.13923\u00a0[cs.CV]"},{"key":"e_1_3_3_3_4_2","doi-asserted-by":"publisher","unstructured":"Aaron Bangor Philip\u00a0T. Kortum and James\u00a0T. Miller. 2008. An Empirical Evaluation of the System Usability Scale. International Journal of Human\u2013Computer Interaction 24 6 (2008) 574\u2013594. 10.1080\/10447310802205776","DOI":"10.1080\/10447310802205776"},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-4470-8_12"},{"key":"e_1_3_3_3_6_2","unstructured":"John Brooke. 2013. SUS: a retrospective. J. Usability Studies 8 2 (Feb. 2013) 29\u201340."},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"publisher","unstructured":"Chengliang Chai Guoliang Li Ju Fan and Yuyu Luo. 2021. CrowdChart: Crowdsourced Data Extraction From Visualization Charts. IEEE Transactions on Knowledge and Data Engineering 33 11 (2021) 3537\u20133549. 10.1109\/TKDE.2020.2972543","DOI":"10.1109\/TKDE.2020.2972543"},{"key":"e_1_3_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681167"},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"publisher","unstructured":"Nan Chen Yuge Zhang Jiahang Xu Kan Ren and Yuqing Yang. 2025. VisEval: A Benchmark for Data Visualization in the Era of Large Language Models. IEEE Transactions on Visualization and Computer Graphics 31 1 (2025) 1301\u20131311. 10.1109\/TVCG.2024.3456320","DOI":"10.1109\/TVCG.2024.3456320"},{"key":"e_1_3_3_3_10_2","unstructured":"Shiqi Chen Tongyao Zhu Ruochen Zhou Jinghan Zhang Siyang Gao Juan\u00a0Carlos Niebles Mor Geva Junxian He Jiajun Wu and Manling Li. 2025. Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas. arxiv:https:\/\/arXiv.org\/abs\/2503.01773\u00a0[cs.CL]"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.695"},{"key":"e_1_3_3_3_12_2","first-page":"24185","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Chen Zhe","year":"2024","unstructured":"Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, et\u00a0al. 2024. InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 24185\u201324198."},{"key":"e_1_3_3_3_13_2","unstructured":"Gheorghe Comanici Eric Bieber Mike Schaekermann Ice Pasupat Noveen Sachdeva Inderjit Dhillon Marcel Blistein Ori Ram Dan Zhang Evan Rosen et\u00a0al. 2025. Gemini 2.5: Pushing the Frontier with Advanced Reasoning Multimodality Long Context and Next Generation Agentic Capabilities. arxiv:https:\/\/arXiv.org\/abs\/2507.06261\u00a0[cs.CL]"},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"crossref","unstructured":"Wenjing Dai Meng Wang Zhibin Niu and Jiawan Zhang. 2018. Chart decoder: Generating textual and numeric information from chart images automatically. Journal of Visual Languages & Computing 48 (2018) 101\u2013109.","DOI":"10.1016\/j.jvlc.2018.08.005"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"publisher","unstructured":"Amit\u00a0Kumar Das Mohammad Tarun and Klaus Mueller. 2025. Charts-of-Thought: Enhancing LLM Visualization Literacy through Structured Data Extraction. IEEE Transactions on Visualization and Computer Graphics (2025) 1\u201311. 10.1109\/TVCG.2025.3634813","DOI":"10.1109\/TVCG.2025.3634813"},{"key":"e_1_3_3_3_16_2","doi-asserted-by":"crossref","unstructured":"Kenny Davila Srirangaraj Setlur David Doermann Bhargava\u00a0Urala Kota and Venu Govindaraju. 2020. Chart mining: A survey of methods for automated chart analysis. IEEE transactions on pattern analysis and machine intelligence 43 11 (2020) 3799\u20133819.","DOI":"10.1109\/TPAMI.2020.2992028"},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"publisher","unstructured":"Dazhen Deng Yihong Wu Xinhuan Shu Jiang Wu Siwei Fu Weiwei Cui and Yingcai Wu. 2023. VisImages: A Fine-Grained Expert-Annotated Visualization Dataset. IEEE Transactions on Visualization and Computer Graphics 29 7 (2023) 3298\u20133311. 10.1109\/TVCG.2022.3155440","DOI":"10.1109\/TVCG.2022.3155440"},{"key":"e_1_3_3_3_18_2","unstructured":"Yucheng Han Chi Zhang Xin Chen Xu Yang Zhibin Wang Gang Yu Bin Fu and Hanwang Zhang. 2023. ChartLlama: A Multimodal LLM for Chart Understanding and Generation. arxiv:https:\/\/arXiv.org\/abs\/2311.16483\u00a0[cs.CV]"},{"key":"e_1_3_3_3_19_2","unstructured":"Wenyi Hong Wenmeng Yu Xiaotao Gu Guo Wang Guobing Gan Haomiao Tang Jiale Cheng Ji Qi Junhui Ji Lihang Pan et\u00a0al. 2025. GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning. arxiv:https:\/\/arXiv.org\/abs\/2507.01006\u00a0[cs.CV]"},{"key":"e_1_3_3_3_20_2","doi-asserted-by":"publisher","unstructured":"Enamul Hoque Parsa Kavehzadeh and Ahmed Masry. 2022. Chart Question Answering: State of the Art and Future Directions. Computer Graphics Forum 41 3 (2022) 555\u2013572. 10.1111\/cgf.14573","DOI":"10.1111\/cgf.14573"},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/302979.303030"},{"key":"e_1_3_3_3_22_2","unstructured":"Edward\u00a0J Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang Weizhu Chen et\u00a0al. 2022. Lora: Low-rank adaptation of large language models. ICLR 1 2 (2022) 3."},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300358"},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300892"},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"publisher","unstructured":"Kung-Hsiang Huang Hou\u00a0Pong Chan May Fung Haoyi Qiu Mingyang Zhou Shafiq Joty Shih-Fu Chang and Heng Ji. 2025. From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models. IEEE Transactions on Knowledge and Data Engineering 37 5 (2025) 2550\u20132568. 10.1109\/TKDE.2024.3513320","DOI":"10.1109\/TKDE.2024.3513320"},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.41"},{"key":"e_1_3_3_3_27_2","unstructured":"Aaron Hurst Adam Lerer Adam\u00a0P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et\u00a0al. 2024. GPT-4o System Card. arxiv:https:\/\/arXiv.org\/abs\/2410.21276\u00a0[cs.CL]"},{"key":"e_1_3_3_3_28_2","unstructured":"OpenAI Inc.2025. Introducing GPT-4.1 in the API. https:\/\/openai.com\/index\/gpt-4-1\/."},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICISCT47635.2019.9012031"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.191"},{"key":"e_1_3_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713551"},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025957"},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00592"},{"key":"e_1_3_3_3_34_2","unstructured":"Samira\u00a0Ebrahimi Kahou Vincent Michalski Adam Atkinson Akos Kadar Adam Trischler and Yoshua Bengio. 2018. FigureQA: An Annotated Figure Dataset for Visual Reasoning. arxiv:https:\/\/arXiv.org\/abs\/1710.07300\u00a0[cs.CV]"},{"key":"e_1_3_3_3_35_2","unstructured":"UW\u00a0Interactive\u00a0Data Lab. 2025. Vega-Lite Example Gallery. https:\/\/vega.github.io\/vega-lite\/examples\/."},{"key":"e_1_3_3_3_36_2","doi-asserted-by":"publisher","unstructured":"Yijie Lian Jianing Hao Wei Zeng and Qiong Luo. 2025. A survey of visual insight mining: Connecting data and insights via visualization. Visual Informatics 9 4 (2025) 100271. 10.1016\/j.visinf.2025.100271","DOI":"10.1016\/j.visinf.2025.100271"},{"key":"e_1_3_3_3_37_2","unstructured":"Fangyu Liu Julian\u00a0Martin Eisenschlos Francesco Piccinno Syrine Krichene Chenxi Pang Kenton Lee Mandar Joshi Wenhu Chen Nigel Collier and Yasemin Altun. 2023. DePlot: One-shot visual language reasoning by plot-to-table translation. arxiv:https:\/\/arXiv.org\/abs\/2212.10505\u00a0[cs.CL]"},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.714"},{"key":"e_1_3_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"e_1_3_3_3_40_2","unstructured":"Haotian Liu Chunyuan Li Yuheng Li Bo Li Yuanhan Zhang Sheng Shen and Yong\u00a0Jae Lee. 2024. LLaVA-NeXT: Improved reasoning OCR and world knowledge. https:\/\/llava-vl.github.io\/blog\/2024-01-30-llava-next\/"},{"key":"e_1_3_3_3_41_2","doi-asserted-by":"crossref","unstructured":"Haotian Liu Chunyuan Li Qingyang Wu and Yong\u00a0Jae Lee. 2023. Visual instruction tuning. Advances in neural information processing systems 36 (2023) 34892\u201334916.","DOI":"10.52202\/075280-1516"},{"key":"e_1_3_3_3_42_2","unstructured":"Sheng Liu Haotian Ye Lei Xing and James Zou. 2024. Reducing Hallucinations in Vision-Language Models via Latent Space Steering. arxiv:https:\/\/arXiv.org\/abs\/2410.15778\u00a0[cs.CV]"},{"key":"e_1_3_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"e_1_3_3_3_44_2","unstructured":"Automeris LLC. 2024. WebPlotDigitizer. https:\/\/automeris.io."},{"key":"e_1_3_3_3_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00196"},{"key":"e_1_3_3_3_46_2","unstructured":"Yuyu Luo Jiawei Tang and Guoliang Li. 2021. nvBench: A Large-Scale Synthesized Dataset for Cross-Domain Natural Language to Visualization Task. arxiv:https:\/\/arXiv.org\/abs\/2112.12926\u00a0[cs.HC]"},{"key":"e_1_3_3_3_47_2","doi-asserted-by":"crossref","unstructured":"Ahmed Masry Mohammed\u00a0Saidul Islam Mahir Ahmed Aayush Bajaj Firoz Kabir Aaryaman Kartha Md\u00a0Tahmid\u00a0Rahman Laskar Mizanur Rahman Shadikur Rahman Mehrad Shahmohammadi et\u00a0al. 2025. ChartQAPro: A More Diverse and Challenging Benchmark for Chart Question Answering. arxiv:https:\/\/arXiv.org\/abs\/2504.05506\u00a0[cs.CL]","DOI":"10.18653\/v1\/2025.findings-acl.978"},{"key":"e_1_3_3_3_48_2","doi-asserted-by":"crossref","unstructured":"Ahmed Masry Parsa Kavehzadeh Xuan\u00a0Long Do Enamul Hoque and Shafiq Joty. 2023. UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning. arxiv:https:\/\/arXiv.org\/abs\/2305.14761\u00a0[cs.CL]","DOI":"10.18653\/v1\/2023.emnlp-main.906"},{"key":"e_1_3_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"e_1_3_3_3_50_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.619"},{"key":"e_1_3_3_3_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581113"},{"key":"e_1_3_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858435"},{"key":"e_1_3_3_3_53_2","doi-asserted-by":"crossref","unstructured":"Fanqing Meng Wenqi Shao Quanfeng Lu Peng Gao Kaipeng Zhang Yu Qiao and Ping Luo. 2024. ChartAssisstant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction Tuning. arxiv:https:\/\/arXiv.org\/abs\/2401.02384\u00a0[cs.CV]","DOI":"10.18653\/v1\/2024.findings-acl.463"},{"key":"e_1_3_3_3_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093523"},{"key":"e_1_3_3_3_55_2","doi-asserted-by":"publisher","unstructured":"Kushin Mukherjee Donghao Ren Dominik Moritz and Yannick Assogba. 2025. EncQA: Benchmarking Vision-Language Models on Visual Encodings for Charts. IEEE Transactions on Visualization and Computer Graphics (2025) 1\u201311. 10.1109\/TVCG.2025.3634249","DOI":"10.1109\/TVCG.2025.3634249"},{"key":"e_1_3_3_3_56_2","doi-asserted-by":"publisher","unstructured":"Donald\u00a0A. Norman. 1994. How might people interact with agents. Commun. ACM 37 7 (July 1994) 68\u201371. 10.1145\/176789.176796","DOI":"10.1145\/176789.176796"},{"key":"e_1_3_3_3_57_2","doi-asserted-by":"crossref","unstructured":"Jason Obeid and Enamul Hoque. 2020. Chart-to-Text: Generating Natural Language Descriptions for Charts by Adapting the Transformer Model. arxiv:https:\/\/arXiv.org\/abs\/2010.09142\u00a0[cs.CL]","DOI":"10.18653\/v1\/2020.inlg-1.20"},{"key":"e_1_3_3_3_58_2","unstructured":"PlotDigitizer. 2025. PlotDigitizer. https:\/\/plotdigitizer.com."},{"key":"e_1_3_3_3_59_2","doi-asserted-by":"publisher","unstructured":"Raian Rahman Rizvi Hasan Abdullah\u00a0Al Farhad Md. Tahmid\u00a0Rahman Laskar Md.\u00a0Hamjajul Ashmafee and Abu Raihan\u00a0Mostofa Kamal. 2023. ChartSumm: A Comprehensive Benchmark for Automatic Chart Summarization of Long and Short Summaries. Proceedings of the Canadian Conference on Artificial Intelligence (June 2023). 10.21428\/594757db.0b1f96f6","DOI":"10.21428\/594757db.0b1f96f6"},{"key":"e_1_3_3_3_60_2","doi-asserted-by":"publisher","unstructured":"Arvind Satyanarayan Dominik Moritz Kanit Wongsuphasawat and Jeffrey Heer. 2017. Vega-Lite: A Grammar of Interactive Graphics. IEEE Transactions on Visualization and Computer Graphics 23 1 (2017) 341\u2013350. 10.1109\/TVCG.2016.2599030","DOI":"10.1109\/TVCG.2016.2599030"},{"key":"e_1_3_3_3_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/2047196.2047247"},{"key":"e_1_3_3_3_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713128"},{"key":"e_1_3_3_3_63_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.401"},{"key":"e_1_3_3_3_64_2","doi-asserted-by":"publisher","unstructured":"Yuan Tian Weiwei Cui Dazhen Deng Xinjing Yi Yurun Yang Haidong Zhang and Yingcai Wu. 2025. ChartGPT: Leveraging LLMs to Generate Charts From Abstract Natural Language. IEEE Transactions on Visualization and Computer Graphics 31 3 (2025) 1731\u20131745. 10.1109\/TVCG.2024.3368621","DOI":"10.1109\/TVCG.2024.3368621"},{"key":"e_1_3_3_3_65_2","unstructured":"Yuan Tian Dazhen Deng Sen Yang Huawei Zheng Bowen Shi Kai Xiong Xinjing Yi and Yingcai Wu. 2025. NoteFlow: Recommending Charts as Sight Glasses for Tracing Data Flow in Computational Notebooks. arxiv:https:\/\/arXiv.org\/abs\/2502.02326\u00a0[cs.HC]"},{"key":"e_1_3_3_3_66_2","doi-asserted-by":"publisher","DOI":"10.1145\/3746059.3747644"},{"key":"e_1_3_3_3_67_2","unstructured":"B. Tummers. 2006. DataThief III. https:\/\/datathief.org."},{"key":"e_1_3_3_3_68_2","doi-asserted-by":"crossref","unstructured":"Zirui Wang Mengzhou Xia Luxi He Howard Chen Yitao Liu Richard Zhu Kaiqu Liang Xindi Wu Haotian Liu Sadhika Malladi et\u00a0al. 2024. Charxiv: Charting gaps in realistic chart understanding in multimodal llms. Advances in Neural Information Processing Systems 37 (2024) 113569\u2013113697.","DOI":"10.52202\/079017-3609"},{"key":"e_1_3_3_3_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386743"},{"key":"e_1_3_3_3_70_2","unstructured":"Yifan Wu Lutao Yan Leixian Shen Yunhai Wang Nan Tang and Yuyu Luo. 2024. ChartInsights: Evaluating Multimodal Large Language Models for Low-Level Chart Question Answering. arxiv:https:\/\/arXiv.org\/abs\/2405.07001\u00a0[cs.CL]"},{"key":"e_1_3_3_3_71_2","unstructured":"Renqiu Xia Haoyang Peng Hancheng Ye Mingsheng Li Xiangchao Yan Peng Ye Botian Shi Yu Qiao Junchi Yan and Bo Zhang. 2024. StructChart: On the Schema Metric and Augmentation for Visual Chart Understanding. arxiv:https:\/\/arXiv.org\/abs\/2309.11268\u00a0[cs.CV]"},{"key":"e_1_3_3_3_72_2","unstructured":"Zhengzhuo Xu Sinan Du Yiyan Qi Chengjin Xu Chun Yuan and Jian Guo. 2024. ChartBench: A Benchmark for Complex Visual Reasoning in Charts. arxiv:https:\/\/arXiv.org\/abs\/2312.15915\u00a0[cs.CV]"},{"key":"e_1_3_3_3_73_2","unstructured":"Zhengzhuo Xu Bowen Qu Yiyan Qi Sinan Du Chengjin Xu Chun Yuan and Jian Guo. 2025. ChartMoE: Mixture of Diversely Aligned Expert Connector for Chart Understanding. arxiv:https:\/\/arXiv.org\/abs\/2409.03277\u00a0[cs.AI]"},{"key":"e_1_3_3_3_74_2","unstructured":"Cheng Yang Chufan Shi Yaxin Liu Bo Shui Junjie Wang Mohan Jing Linran Xu Xinyu Zhu Siheng Li Yuxiang Zhang et\u00a0al. 2025. ChartMimic: Evaluating LMM\u2019s Cross-Modal Reasoning Capability via Chart-to-Code Generation. arxiv:https:\/\/arXiv.org\/abs\/2406.09961\u00a0[cs.SE]"},{"key":"e_1_3_3_3_75_2","doi-asserted-by":"publisher","unstructured":"Yilin Ye Jianing Hao Yihan Hou Zhan Wang Shishi Xiao Yuyu Luo and Wei Zeng. 2024. Generative AI for visualization: State of the art and future directions. Visual Informatics 8 2 (2024) 43\u201366. 10.1016\/j.visinf.2024.04.003","DOI":"10.1016\/j.visinf.2024.04.003"},{"key":"e_1_3_3_3_76_2","doi-asserted-by":"publisher","unstructured":"Shukang Yin Chaoyou Fu Sirui Zhao Ke Li Xing Sun Tong Xu and Enhong Chen. 2024. A survey on multimodal large language models. National Science Review 11 12 (11 2024) nwae403. 10.1093\/nsr\/nwae403","DOI":"10.1093\/nsr\/nwae403"},{"key":"e_1_3_3_3_77_2","doi-asserted-by":"publisher","unstructured":"Xingchen Zeng Haichuan Lin Yilin Ye and Wei Zeng. 2025. Advancing Multimodal Large Language Models in Chart Question Answering with Visualization-Referenced Instruction Tuning. IEEE Transactions on Visualization and Computer Graphics 31 1 (2025) 525\u2013535. 10.1109\/TVCG.2024.3456159","DOI":"10.1109\/TVCG.2024.3456159"},{"key":"e_1_3_3_3_78_2","doi-asserted-by":"publisher","unstructured":"Jingyi Zhang Jiaxing Huang Sheng Jin and Shijian Lu. 2024. Vision-Language Models for Vision Tasks: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 46 8 (2024) 5625\u20135644. 10.1109\/TPAMI.2024.3369699","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"e_1_3_3_3_79_2","doi-asserted-by":"crossref","unstructured":"Liang Zhang Anwen Hu Haiyang Xu Ming Yan Yichen Xu Qin Jin Ji Zhang and Fei Huang. 2024. TinyChart: Efficient Chart Understanding with Visual Token Merging and Program-of-Thoughts Learning. arxiv:https:\/\/arXiv.org\/abs\/2404.16635\u00a0[cs.CV]","DOI":"10.18653\/v1\/2024.emnlp-main.112"},{"key":"e_1_3_3_3_80_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.363"},{"key":"e_1_3_3_3_81_2","doi-asserted-by":"crossref","unstructured":"Yuhua Zhou Xiyu Meng Yanhong Wu Tan Tang Yongheng Wang and Yingcai Wu. 2023. An intelligent approach to automatically discovering visual insights. Journal of Visualization 26 3 (2023) 705\u2013722.","DOI":"10.1007\/s12650-022-00894-z"}],"event":{"name":"CHI 2026: CHI Conference on Human Factors in Computing Systems","location":"Barcelona Spain","acronym":"CHI '26","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3772318.3790721","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T08:47:44Z","timestamp":1776415664000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3772318.3790721"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":80,"alternative-id":["10.1145\/3772318.3790721","10.1145\/3772318"],"URL":"https:\/\/doi.org\/10.1145\/3772318.3790721","relation":{},"subject":[],"published":{"date-parts":[[2026,4,13]]},"assertion":[{"value":"2026-04-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}