InsightEval: An Expert-Curated Benchmark for Assessing Insight Discovery in LLM-Driven Data Agents

TL;DR

InsightEval is a new benchmark dataset and metric for evaluating the ability of large language models and multi-agent systems to discover insights in data, addressing limitations of previous benchmarks.

Contribution

The paper introduces InsightEval, a curated dataset and a novel metric for assessing insight discovery, improving upon existing benchmarks like InsightBench.

Findings

Highlighting challenges in automated insight discovery

Demonstrating the effectiveness of InsightEval and the new metric

Providing guidance for future research in data insight discovery

Abstract

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, more and more researchers are making use of these technologies for insight discovery. However, there are few benchmarks for evaluating insight discovery capabilities. As one of the most comprehensive existing frameworks, InsightBench also suffers from many critical flaws: format inconsistencies, poorly conceived objectives, and redundant insights. These issues may significantly affect the quality of data and the evaluation of agents. To address these issues, we thoroughly investigate shortcomings in InsightBench and propose essential criteria for a high-quality insight benchmark. Regarding this, we develop a data-curation pipeline to construct a new dataset named InsightEval. We further introduce a novel metric to measure the exploratory performance of agents. Through extensive experiments on InsightEval, we highlight prevailing challenges in automated insight discovery and raise some key findings to guide future research in this promising direction.