{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:31:55Z","timestamp":1778085115263,"version":"3.51.4"},"reference-count":133,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"DOE Center for Advanced Bioenergy and Bioproducts Innovation"},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["DESC0018420"],"award-info":[{"award-number":["DESC0018420"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Molecule Maker Lab Institute"},{"name":"NSF","award":["2019897"],"award-info":[{"award-number":["2019897"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tkde.2024.3513320","type":"journal-article","created":{"date-parts":[[2024,12,9]],"date-time":"2024-12-09T14:08:13Z","timestamp":1733753293000},"page":"2550-2568","source":"Crossref","is-referenced-by-count":14,"title":["From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1285-6196","authenticated-orcid":false,"given":"Kung-Hsiang","family":"Huang","sequence":"first","affiliation":[{"name":"Salesforce AI Research, San Francisco, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hou Pong","family":"Chan","sequence":"additional","affiliation":[{"name":"University of Illinois, Champaign, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1869-0363","authenticated-orcid":false,"given":"May","family":"Fung","sequence":"additional","affiliation":[{"name":"University of Illinois, Champaign, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyi","family":"Qiu","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingyang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Capital One, McLean, VA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shafiq","family":"Joty","sequence":"additional","affiliation":[{"name":"Salesforce AI Research and NTU, San Francisco, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1444-1205","authenticated-orcid":false,"given":"Shih-Fu","family":"Chang","sequence":"additional","affiliation":[{"name":"Columbia University, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0464-7966","authenticated-orcid":false,"given":"Heng","family":"Ji","sequence":"additional","affiliation":[{"name":"University of Illinois, Champaign, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.41"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093523"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00592"},{"key":"ref5","article-title":"FigureQA: An annotated figure dataset for visual reasoning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kahou"},{"key":"ref6","article-title":"MathVista: Evaluating mathematical reasoning of foundation models in visual contexts","author":"Lu","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.811"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.inlg-1.20"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.277"},{"key":"ref10","article-title":"ChartCheck: An evidence-based fact-checking dataset over real-world chart images","author":"Akhtar","year":"2023"},{"key":"ref11","article-title":"MapQA: A dataset for question answering on choropleth maps","author":"Chang","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093269"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.264"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1525\/9780520940420-020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.401"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.660"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.2307\/2332226"},{"key":"ref19","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.450"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-eacl.37"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref24","article-title":"GPT-4V(ision) system card","year":"2023"},{"key":"ref25","article-title":"Introducing the next generation of claude","year":"2024"},{"key":"ref26","first-page":"2661","article-title":"Binary codes capable of correcting deletions, insertions, and reversals","volume-title":"Proc. Sov. Phys. Doklady","author":"Levenshtein"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093494"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.85"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.714"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.906"},{"key":"ref32","first-page":"18893","article-title":"Pix2Struct: Screenshot parsing as pretraining for visual language understanding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.70"},{"key":"ref34","article-title":"ChartLlama: A multimodal LLM for chart understanding and generation","author":"Han","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.463"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.277"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/VIS54862.2022.00016"},{"key":"ref39","article-title":"Figure captioning with reasoning and sequence-level training","author":"Chen","year":"2019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_41"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-92307-5_2"},{"key":"ref42","article-title":"ChartBench: A benchmark for complex visual reasoning in charts","author":"Xu","year":"2023"},{"key":"ref43","article-title":"DOMINO: A dual-system for multi-step visual language reasoning","author":"Wang","year":"2023"},{"key":"ref44","article-title":"FigCaps-HF: A figure-to-caption generative framework and benchmark with human feedback","author":"Singh","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.708"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00343"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref52","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref53","article-title":"SciGraphQA: A large-scale synthetic multi-turn question-answering dataset for scientific graphs","author":"Li","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21428\/594757db.0b1f96f6"},{"key":"ref55","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref56","article-title":"mPLUG-Owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.43"},{"key":"ref59","first-page":"334","article-title":"Gated recurrent convolution neural network for OCR","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219861"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.245"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.452"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.543"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223908"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_11"},{"key":"ref66","article-title":"Do LLMs work on charts? Designing few-shot prompts for chart question answering and summarization","author":"Do","year":"2023"},{"key":"ref67","article-title":"SPHINX: The joint mixing of weights, tasks, and visual embeddings for multi-modal large language models","author":"Lin","year":"2023"},{"key":"ref68","article-title":"Shikra: Unleashing multimodal LLM\u2019s referential dialogue magic","author":"Chen","year":"2023"},{"key":"ref69","article-title":"StructChart: Perception, structuring, reasoning for visual chart understanding","author":"Xia","year":"2023"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.520"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403172"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26598"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00244"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref79","article-title":"Quantifying language models\u2019 sensitivity to spurious features in prompt design or: How I learned to start worrying about prompt formatting","author":"Sclar","year":"2023"},{"key":"ref80","first-page":"28091","article-title":"MIND2WEB: Towards a generalist agent for the web","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Deng"},{"key":"ref81","article-title":"AgentBench: Evaluating LLMs as agents","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref82","article-title":"A simple neural network module for relational reasoning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Santoro"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.398"},{"key":"ref84","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref85","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref86","article-title":"mPLUG-DocOwl: Modularized multimodal large language model for document understanding","author":"Ye","year":"2023"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00959"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-eacl.30"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.775"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3298050"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14573"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3148007"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3099002"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0393-x"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.126"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_19"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref99","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref100","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90% ChatGPT quality","volume-title":"Proc. 2023 Conf. Hypothetical Lang. Model Syst.","author":"Chiang","year":"2023"},{"key":"ref101","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref102","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2025.3542504"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.33"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.153"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.32"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1145\/3704435"},{"key":"ref108","article-title":"If LLM is the wizard, then code is the wand: A survey on how code empowers large language models to serve as intelligent agents","author":"Yang","year":"2024"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.394"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-demos.8"},{"key":"ref111","doi-asserted-by":"crossref","DOI":"10.1101\/2023.07.06.547759","article-title":"SynerGPT: In-context learning for personalized drug synergy prediction and drug design","author":"Edwards","year":"2023"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.799"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3542615"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.619"},{"key":"ref115","article-title":"Scaling instruction-finetuned language models","author":"Chung","year":"2022"},{"key":"ref116","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.89"},{"key":"ref118","article-title":"TAPEX: Table pre-training via learning a neural SQL executor","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.27"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1142"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.311"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.402"},{"key":"ref123","article-title":"Can LLMs produce faithful explanations for fact-checking? Towards faithful explainable fact-checking via multi-agent debate","author":"Kim"},{"key":"ref124","article-title":"ChartX & ChartVLM: A versatile benchmark and foundation model for complicated chart reasoning","author":"Xia","year":"2024"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref126","article-title":"BERTScore: Evaluating text generation with BERT","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.704"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.112"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681167"},{"key":"ref131","article-title":"Getting ViT in shape: Scaling laws for compute-optimal model design","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alabdulmohsin"},{"key":"ref132","article-title":"Textbooks are all you need II: Phi-1.5 technical report","author":"Li","year":"2023"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.619"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/69\/10948402\/10787102-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/10948402\/10787102.pdf?arnumber=10787102","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,21]],"date-time":"2025-07-21T18:10:09Z","timestamp":1753121409000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10787102\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":133,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2024.3513320","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}