跳到主要导航 跳到搜索 跳到主要内容

AskTable: LLM-Powered Interactive Visual Data Story Construction from Tables

  • Gerile Aodeng
  • , Chenwei Liang
  • , Shaokun Zhang
  • , Yunshan Feng
  • , Qiyang Chen
  • , Guozheng Li*
  • , Chi Harold Liu
  • *此作品的通讯作者
  • Beijing Institute of Technology

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

We present AskTable, an interactive system designed to support iterative construction of visual data stories for tabular data. AskTable enables users to explore, organize, and narrate data insights by combining structured subspace filtering, semantic insight graphs, and LLM-driven recommendations. The AskTable system employs a radial insight tree that visualizes user-driven analytical paths through a force-directed layout, allowing branching, modification, and backtracking during exploration. Users can interactively pin, query, and refine insights, while the system responds with relevant follow-up recommendations powered by a reasoning module, enabling the incremental construction of narrative data stories.

源语言英语
主期刊名UIST Adjunct 2025 - Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology
编辑Andrea Bianchi, Elena Glassman, Shengdong Zhao, Jeeeun Kim, Ian Oakley, Wendy E. Mackay
出版商Association for Computing Machinery, Inc
ISBN(电子版)9798400720369
DOI
出版状态已出版 - 27 9月 2025
活动38th Annual ACM Symposium on User Interface Software and Technology, UIST 2025 - Busan, 韩国
期限: 28 9月 20251 10月 2025

出版系列

姓名UIST Adjunct 2025 - Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology

会议

会议38th Annual ACM Symposium on User Interface Software and Technology, UIST 2025
国家/地区韩国
Busan
时期28/09/251/10/25

指纹

探究 'AskTable: LLM-Powered Interactive Visual Data Story Construction from Tables' 的科研主题。它们共同构成独一无二的指纹。

引用此