Evaluating Prompt Injection Defenses for Educational LLM Tutors: Security-Usability-Latency Trade-offs

概要

arXiv:2605.06669v1 Announce Type: cross Abstract: Educational LLM tutors face a core AI alignment challenge: they must follow user intent while preserving pedagogical constraints and safety policies. We present an evaluation methodology for prompt-injection defenses in this setting, showing that gu…