Automatic Histograms: Leveraging Language Models for Text Dataset Exploration
This tool addresses the cumbersome process of custom analysis for domain-specific text datasets, offering a practical solution for data workers, though it is incremental in the context of existing LLM-assisted sensemaking tools.
The researchers tackled the problem of exploring unstructured text datasets by developing AutoHistograms, a tool that uses large language models to automatically identify relevant features and visualize them as histograms, enabling data workers to quickly gain insights and explore data interactively.
Making sense of unstructured text datasets is perennially difficult, yet increasingly relevant with Large Language Models. Data workers often rely on dataset summaries, especially distributions of various derived features. Some features, like toxicity or topics, are relevant to many datasets, but many interesting features are domain specific: instruments and genres for a music dataset, or diseases and symptoms for a medical dataset. Accordingly, data workers often run custom analyses for each dataset, which is cumbersome and difficult. We present AutoHistograms, a visualization tool leveragingLLMs. AutoHistograms automatically identifies relevant features, visualizes them with histograms, and allows the user to interactively query the dataset for categories of entities and create new histograms. In a user study with 10 data workers (n=10), we observe that participants can quickly identify insights and explore the data using AutoHistograms, and conceptualize a broad range of applicable use cases. Together, this tool and user study contributeto the growing field of LLM-assisted sensemaking tools.