The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

2024-04-20来源 OpenAI BlogEnglish
Today's LLMs are susceptible to prompt injections, jailbreaks, and other attacks that allow adversaries to overwrite a model's original instructions with their own malicious prompts.

原文：https://www.a8q9.cn/en/article/the-instruction-hierarchy-training-llms-to-prioritize-privileged-instructions-1ae40d.html

相关文章