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 0026, Yulia Tsvetkov, Christopher Parisien, Yejin Choi 0001. Guardrails and Security for LLMs: Safe, Secure and Controllable Steering of LLM Applications. In Yuki Arase, David Jurgens, Fei Xia 0004, editors, Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 5: Tutorial Abstracts), ACL 2025, Vienna, Austria, July 27 - August 1, 2025. pages 13-15, Association for Computational Linguistics, 2025. [doi]

Abstract

Abstract is missing.