COSMIC: Generalized Refusal Direction Identification in LLM Activations
Published in ACL 2025 Findings; KnowFM@ACL 2025 Workshop, 2025
Recommended citation: @misc{siu2025cosmicgeneralizedrefusaldirection, title={COSMIC: Generalized Refusal Direction Identification in LLM Activations}, author={Vincent Siu and Nicholas Crispino and Zihao Yu and Sam Pan and Zhun Wang and Yang Liu and Dawn Song and Chenguang Wang}, year={2025}, eprint={2506.00085}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2506.00085}, }
Download Paper