Automatic Histograms: Leveraging Language Models for Text Dataset Exploration
Reif, Emily, Qian, Crystal, Wexler, James, Kahng, Minsuk
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Feb-21-2024
- Country:
- North America > United States > New York > New York County > New York City (0.14)
- Genre:
- Questionnaire & Opinion Survey (1.00)
- Research Report (0.83)
- Industry:
- Technology:
- Information Technology > Artificial Intelligence > Natural Language
- Generation (0.46)
- Large Language Model (0.58)
- Text Processing (0.67)
- Information Technology > Artificial Intelligence > Natural Language