I nsight E val: An Expert-Curated Benchmark for Assessing Insight Discovery in LLM -Driven Data Agents
Zhenghao Zhu · Yuanfeng SONG · Xing Chen · Chengzhong Liu · Cui Yakun · Caleb Chen Cao · Sirui Han · Yike Guo
摘要
Data analysis has become an indispensable part of scientific research. To discover the latent knowledge and insights hidden within massive datasets, we need to perform deep exploratory analysis to realize their full value. With the advent of large language models (LLMs) and multi-agent systems, m...