Visual Analytics
Visual analytics integrates visual interfaces with data analysis techniques to facilitate human understanding of complex datasets, particularly those generated by machine learning models. Current research emphasizes the use of large language models (LLMs) to enhance interaction, generate insights, and improve the interpretability of model outputs, often focusing on explainable AI (XAI) methods and interactive visualizations for time series and high-dimensional data. This field is crucial for improving the trustworthiness and usability of AI systems across diverse domains, from finance and healthcare to education and traffic management, by enabling human experts to effectively interpret and interact with complex data and models.
Papers
iScore: Visual Analytics for Interpreting How Language Models Automatically Score Summaries
Adam Coscia, Langdon Holmes, Wesley Morris, Joon Suh Choi, Scott Crossley, Alex Endert
TrafPS: A Shapley-based Visual Analytics Approach to Interpret Traffic
Zezheng Feng, Yifan Jiang, Hongjun Wang, Zipei Fan, Yuxin Ma, Shuang-Hua Yang, Huamin Qu, Xuan Song