2025/1/22 update: Our paper has been accepted to NAACL2025 main conference!
This is the official repository for the paper: Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities. Work done during the internship at Microsoft Research.
The code and models are still under review by Microsoft Research. We plan to release it very soon!
Chung-En Sun, Xiaodong Liu, Weiwei Yang, Tsui-Wei Weng, Hao Cheng, Aidan San, Michel Galley, Jianfeng Gao, "Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities"
@article{advllm,
title={Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities},
author={Chung-En Sun, Xiaodong Liu, Weiwei Yang, Tsui-Wei Weng, Hao Cheng, Aidan San, Michel Galley, Jianfeng Gao},
journal={NAACL},
year={2025}
}