AI 요약
IH-Challenge trains models to prioritize trusted instructions, improving instruction hierarchy, safety steerability, and resistance to prompt injection attacks.
댓글0개
댓글을 작성하려면 로그인이 필요합니다.
Improving instruction hierarchy in frontier LLMs
IH-Challenge trains models to prioritize trusted instructions, improving instruction hierarchy, safety steerability, and resistance to prompt injection attacks.