AskChart: Universal Chart Understanding through Textual Enhancement
Keywords: Chart Understanding, Multimodal Learning, Vision-Language Models, Visual-Textual Representation, Instruction Tuning
Abstract: Chart understanding tasks such as ChartQA and Chart-to-Text involve automatically extracting and interpreting key information from charts, enabling users to query or convert visual data into structured formats. State-of-the-art approaches primarily focus on visual cues from chart images, failing to *explicitly* incorporate rich textual information (e.g., data labels and axis labels) embedded within the charts. This textual information is vital for intuitive human comprehension and interpretation of charts. Moreover, existing models are often large and computationally intensive, limiting their practical applicability. In this paper, we introduce AskChart, a universal model that *explicitly* integrates both *textual* and *visual* cues from charts using a sparse Mixture of Experts (MoE) architecture. AskChart facilitates the learning of enhanced visual-textual representations of charts for effectively handling multiple chart understanding tasks, while maintaining a smaller model size. To capture the synergy between visual and textual modalities, we curate a large-scale dataset named ChartBase with about 7.5M data samples, which helps align textual and visual information and facilitates the extraction of visual entities and text. To effectively train AskChart, we design a three-stage training strategy to align visual and textual modalities embedded within charts for learning robust visual-textual representations and optimizing the learning of the MoE layer for advancing chart understanding. Extensive experiments across five datasets demonstrate the significant performance gains of AskChart in four chart understanding tasks. Remarkably, AskChart with 4.6B parameters outperforms state-of-the-art models with 13B parameters by 68.3\% in Open-ended ChartQA and 49.2\% in Chart-to-Text tasks, while achieving comparable performance in ChartQA and Chart-to-Table tasks.
Primary Area: applications to computer vision, audio, language, and other modalities
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 10573
Loading