InsightLens: Discovering and Exploring Insights from Conversational Contexts in Large-Language-Model-Powered Data Analysis

The proliferation of large language models (LLMs) has revolutionized the capabilities of natural language interfaces (NLIs) for data analysis. LLMs can perform multi-step and complex reasoning to generate data insights based on users' analytic intents. However, these insights often entangle with an abundance of contexts in analytic conversations such as code, visualizations, and natural language explanations. This hinders efficient identification, verification, and interpretation of insights within the current chat-based interfaces of LLMs. In this paper, we first conduct a formative study with eight experienced data analysts to understand their general workflow and pain points during LLM-powered data analysis. Then, we propose an LLM-based multi-agent framework to automatically extract, associate, and organize insights along with the analysis process. Based on this, we introduce InsightLens, an interactive system that visualizes the intricate conversational contexts from multiple aspects to facilitate insight discovery and exploration. A user study with twelve data analysts demonstrates the effectiveness of InsightLens, showing that it significantly reduces users' manual and cognitive effort without disrupting their conversational data analysis workflow, leading to a more efficient analysis experience.