LLooM

From unstructured text to interpretable concepts

LLooM automatically surfaces high-level concepts to analyze unstructured text

Examples

What is LLooM?

Get Started

Github

Summary of the LLooM Concept Induction process from Data to Concepts to an interactive LLooM Workbench visualization

🔍

Generate interpretable concepts

LLooM concepts are defined by natural language descriptions and explicit inclusion criteria.

📊

Visualize data by concepts

Use the LLooM Workbench in computational notebooks for dataset overviews, concept details, and doc-level scores and highlights.

🚗

Steer the analysis direction

Provide a seed term to orient concept induction around your interests, like "social issues" for political discussion or "evaluation methods" for academic papers.