IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis

IDA-Bench is a comprehensive benchmark designed to evaluate Large Language Models on interactive guided data analysis tasks. The benchmark tests LLMs’ abilities to understand data, generate appropriate analyses, and respond to user guidance.

Authors: Hanyu Li, Haoyu Liu, Tingyu Zhu, Tianyu Guo, Zeyu Zheng, Xiaotie Deng, Michael I. Jordan (*co-first author)

Download Paper