Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?

Sravanti Addepalli, Yerram Varun, Arun Suggala, Karthikeyan Shanmugam, Prateek Jain

BibTeX
@inproceedings{addepalli2025does,
  author = {Sravanti Addepalli and Yerram Varun and Arun Suggala and Karthikeyan Shanmugam and Prateek Jain},
  title = {{Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?}},
  booktitle = {International Conference on Learning Representations},
  year = {2025},
  url = {https://openreview.net/forum?id=LO4MEPoqrG},
}
Figure