Towards Accurate Sense-Making of Data Visualization using LLM
Supakit Boonsongprasert, Jacob Percy, & Dr. Karen Chen, Department of Information Systems.
Sense-making refers to the process of interpreting the meaning of data
visualizations—a skill that is becoming increasingly critical in a society where data literacy and analytical competencies are essential. However, there remains a lack of efficient solutions to support students in developing sense-making skills.
Our prior work has demonstrated the potential of large language models (LLMs) to evaluate the depth of students’ understanding. Yet, a gap persists in accurately quantifying the correctness of students’ interpretations of data visualizations.
This project aims to explore various LLMs and their configurations to assess student responses and deliver actionable feedback that enhances chart-reading and data interpretation skills.