About

TrackLLM is a research project that continuously monitors LLM APIs for undisclosed changes, using two cost-effective methods described in Methodology.

The website was originally developed by Timothée Chauvin, as a PhD student at Inria (ARTISHAU team).

This project is supported by Inria, IRISA, CNRS, INESIA, and SequoIA.

Inria IRISA CNRS SequoIAQ

GitHub

Code: https://github.com/timothee-chauvin/trackllm_website (AGPL-3.0)
Data: https://github.com/timothee-chauvin/trackllm_data (CC BY 4.0)

Timothée Chauvin, Erwan Le Merrer, François Taïani, Gilles Tredan (2026), "Log Probability Tracking of LLM APIs". ICLR 2026. https://arxiv.org/abs/2512.03816

Timothée Chauvin, Clément Lalanne, Erwan Le Merrer, Jean-Michel Loubes, François Taïani, Gilles Tredan (2026), "Token-Efficient Change Detection in LLM APIs". ICML 2026. https://arxiv.org/abs/2602.11083

@inproceedings{
chauvin2026log,
title={Log Probability Tracking of {LLM} {API}s},
author={Timothee Chauvin and Erwan Le Merrer and Francois Taiani and Gilles Tredan},
booktitle={The Fourteenth International Conference on Learning Representations},
year={2026},
url={https://openreview.net/forum?id=hFxivbAgVP}
}

@inproceedings{
chauvin2026tokenefficient,
title={Token-Efficient Change Detection in {LLM} {API}s},
author={Timothee Chauvin and Cl{\'e}ment Lalanne and Erwan Le Merrer and Jean-Michel Loubes and Francois Taiani and Gilles Tredan},
booktitle={Forty-third International Conference on Machine Learning},
year={2026},
url={https://openreview.net/forum?id=7cMlZZYZT0}
}