paper-with-me

홈 › Papers

DeepVIS: Bridging Natural Language and Data Visualization Through Step-wise Reasoning

2025-08-03 · Zhihao Shuai, Boyan Li, Siyu Yan, Yuyu Luo, Weikai Yang arxiv

Although data visualization is powerful for revealing patterns and communicating insights, creating effective visualizations requires familiarity with authoring tools and often disrupts the analysis flow. While large language models show promise for automatically converting analysis intent into visualizations, existing methods function as black boxes without transparent reasoning processes, which prevents users from understanding design rationales and refining suboptimal outputs. To bridge this gap, we propose integrating Chain-of-Thought (CoT) reasoning into the Natural Language to Visualization (NL2VIS) pipeline. First, we design a comprehensive CoT reasoning process for NL2VIS and develop an automatic pipeline to equip existing datasets with structured reasoning steps. Second, we introduce nvBench-CoT, a specialized dataset capturing detailed step-by-step reasoning from ambiguous natural language descriptions to finalized visualizations, which enables state-of-the-art performance when used for model fine-tuning. Third, we develop DeepVIS, an interactive visual interface that tightly integrates with the CoT reasoning process, allowing users to inspect reasoning steps, identify errors, and make targeted adjustments to improve visualization outcomes. Quantitative benchmark evaluations, two use cases, and a user study collectively demonstrate that our CoT framework effectively enhances NL2VIS quality while providing insightful reasoning steps to users.

📄 PDF Abstract BibTeX arXiv:2508.01700

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

DeepVisualInsight: Time-Travelling Visualization for Spatio-Temporal Causality of Deep Classification Training

2021-12-31 · Xianglin Yang, Yun Lin, Ruofan Liu, Zhenfeng He 외

Understanding how the predictions of deep learning models are formed during the training process is crucial to improve model performance and fix model defects, especially when we need to investigate nontrivial training s…

Active LearningDeep Learning

Dissecting Catastrophic Forgetting in Continual Learning by Deep Visualization

2020-01-06 · Giang Nguyen, Shuan Chen, Thao Do, Tae Joon Jun 외

Interpreting the behaviors of Deep Neural Networks (usually considered as a black box) is critical especially when they are now being widely adopted over diverse aspects of human life. Taking the advancements from Explai…

Continual Learning

DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoning

2026-02-18 · Haoxiang Sun, Lizhen Xu, Bing Zhao, Wotao Yin 외 arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) has been shown effective in enhancing the visual reflection and reasoning capabilities of Large Multimodal Models (LMMs). However, existing datasets are predominantly…

Reinforcement LearningMultimodal Reasoning

VizGen: Data Exploration and Visualization from Natural Language via a Multi-Agent AI Architecture

2025-09-26 · Sandaru Fernando, Imasha Jayarathne, Sithumini Abeysekara, Shanuja Sithamparanthan 외 arxiv

Data visualization is essential for interpreting complex datasets, yet traditional tools often require technical expertise, limiting accessibility. VizGen is an AI-assisted graph generation system that empowers users to …

Graph Generation

YAC: Bridging Natural Language and Interactive Visual Exploration with Generative AI for Biomedical Data Discovery

2025-09-23 · Devin Lange, Shanghua Gao, Pengwei Sui, Priya Misner 외 arxiv

Incorporating natural language input has the potential to improve the capabilities of biomedical data discovery interfaces. However, user interface elements and visualizations are still powerful tools for interacting wit…