Retrieval-Augmented Defense: Adaptive and Controllable Jailbreak Prevention for Large Language Models

Published in ACL, 2026

Recommended citation: Guangyu Yang, Jinghong Chen, Jingbiao Mei, Weizhe Lin, Bill Byrne. (2026). Retrieval-Augmented Defense: Adaptive and Controllable Jailbreak Prevention for Large Language Models. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 40849–40868. https://doi.org/10.18653/v1/2026.acl-long.1895 https://aclanthology.org/2026.acl-long.1895/