Combating Instruction Conflict via Energy-Driven Latent Conflict Detection
Large Language Models (LLMs) are increasingly deployed with hierarchical instructions, yet they remain vulnerable to conflicts in which user directives override system-level constraints. Existing defense mechanisms predominantly focus on static input inspection and therefore fail to detect Response Drift, a phenomenon...
Mi Ma, Yu-Xin Wu, Jing-Bo Wang et al.
· 0 citations