EasyDeepLearn

What is an instruction hierarchy in modern LLMs?

hard

Answer

  • OpenAI (2024) formalized: developer instructions > user instructions > tool outputs > third-party content.
  • RLHF training teaches the model to weight higher tiers over lower ones when they conflict.
  • Primary defense against indirect prompt injection (retrieved content trying to override the system prompt).
  • Anthropic uses a similar 'privileged / unprivileged' distinction.
  • Enforced during alignment via curated conflict examples.
Check yourself — multiple choice
  • All instructions equal
  • Developer > user > tool output > third-party content; RLHF trains the LLM to honor this priority — main defense against prompt injection
  • Random priority
  • Only user prompts

Instruction hierarchy: dev > user > tool > 3rd-party; enforces safety in retrieval / agents.

#prompting#safety#alignment

Practise LLMs & GenAI

214 interview questions in this topic.

Related questions