Updates — CatLLM

Updates

Releases, papers, and analyses

Everything written about CatLLM and the packages built on it, newest first.

2026

Aug 4 100,000 Downloads: What CatLLM Has Built So Far Milestone
Jun 4 Model Diversity Over Model Size: Unanimous LLM Ensembles Correct Over-Classification Preprint
Jun 2 High Agreement, Different Stories: How LLM Classifiers Reshape Demographic Patterns Preprint
May 25 CatLLM Desktop: A Mac App for Classifying Text Without Writing Code Release
May 17 CatLLM R Package: Classify Survey Text with LLMs in R Release
Mar 22 What California Cities Actually Legislate: Classifying Municipal Ordinances with cat-pol Analysis
Mar 5 What Bluesky's Most-Followed Accounts Actually Post About Analysis
Mar 4 Classifying Open-Ended Survey Responses Directly in Claude Code Guide
Mar 2 Analyzing My Threads Feed with cat-vader Analysis
Jan 17 Ensemble Classification in CatLLM: Combining Multiple Models for Robust Results Release
Jan 6 CatLLM is Now a Web App Release

2025

Dec 30 CatLLM Now Supports HuggingFace: Access Thousands of Open-Source Models Release
Dec 11 New Python Package: llm-web-research for Verified Web Research Release
Nov 28 An Empirical Investigation into the Utility of LLMs in Open-Ended Survey Data Categorization Preprint
Nov 5 Cleaning Data with AI: An Example with CatLLM Guide
Oct 29 Presenting CatLLM at the University of Washington Talk
Oct 9 CatLLM Now Builds Custom Datasets from Web Data Release
Jun 3 Contribute to Open-Source Dementia Research: Improving CERAD Image Scoring Analysis
Jun 2 How We're Using GPT-4o for Dementia Classification Analysis
May 30 A Tool for Demographers and Social Scientists to Categorize Open-Ended Survey Data Release

Elsewhere

Mentions and citations

Papers citing CatLLM and public projects using it, collected from OpenAlex, Semantic Scholar, GitHub, and Hacker News.

All posts on christophersoria.com