Guardrails and Security for LLMs: Safe, Secure and Controllable Steering of LLM Applications.
Traian Rebedea, Leon Derczynski, Shaona Ghosh, Makesh Narsimhan Sreedhar, Faeze Brahman, Liwei Jiang, Bo Li, Yulia Tsvetkov, Christopher Parisien, Yejin Choi
Browse the full ACL paper archive.