---
title: README
emoji: 🌍
colorFrom: red
colorTo: yellow
sdk: static
pinned: false
---

# Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs

Abhay Sheshadri,* [asheshadri31@gatech.edu](asheshadri31@gatech.edu); 
Aidan Ewart,* [aidanprattewart@gmail.com](aidanprattewart@gmail.com); 
Phillip Guo,* [phguo@umd.edu](phguo@umd.edu); 
Aengus Lynch,* [aenguslynch@gmail.com](aenguslynch@gmail.com);
Cindy Wu,* [wu.cindyx@gmail.com](wu.cindyx@gmail.com);
Vivek Hebbar*;
Henry Sleight;
Asa Cooper Stickland;
Ethan Perez;
Dylan Hadfield-Menell;
Stephen Casper, [scasper@mit.edu](scasper@mit.edu)

See our [GitHub:](https://github.com/aengusl/latent-adversarial-training).

Read the paper on arXiv: [Targeted Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs](https://arxiv.org/abs/2407.15549).

Chat with our robust refusal model ([https://huggingface.co./LLM-LAT/robust-llama3-8b-instruct](https://huggingface.co./LLM-LAT/robust-llama3-8b-instruct)) at [https://www.abhayesian.com/lat-chat](https://www.abhayesian.com/lat-chat).

```
@article{sheshadri2024targeted,
  title={Targeted Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs},
  author={Sheshadri, Abhay and Ewart, Aidan and Guo, Phillip and Lynch, Aengus and Wu, Cindy and Hebbar, Vivek and Sleight, Henry and Stickland, Asa Cooper and Perez, Ethan and Hadfield-Menell, Dylan and Casper, Stephen},
  journal={arXiv preprint arXiv:2407.15549},
  year={2024}
}
```

See also preliminary work: [Defending Against Unforeseen Failure Modes with Latent Adversarial Training](https://arxiv.org/abs/2403.05030).