Ziqi, Miao, Lijun Li, Yuan Xiong, Zhenhua Liu, Pengyu Zhu, and Jing Shao. 2026. “Response Attack: Exploiting Contextual Priming to Jailbreak Large Language Models”. Proceedings of the AAAI Conference on Artificial Intelligence 40 (41):35284-92. https://doi.org/10.1609/aaai.v40i41.40836.