Anthropic· @AnthropicAI · X·· 2026-04-30AI 评分56
AI 导读
在新的Anthropic Fellows研究中，我们探讨了“内省适配器”：这种工具能让语言模型自我报告在训练过程中习得的行为——包括潜在的错位。 [引用 @kshenoy_]：大型语言模型能否直接告诉我们它们在训练中习得的不良行为？ 我们训练了一个单一的内省适配器（IA），使微调后的模型能够描述自身行为。 该方法可推广至检测隐藏的错位、后门和安全措施移除。
正文 · 原文
In new Anthropic Fellows research, we discuss “introspection adapters": a tool that allows language models to self-report behaviors they've learned during training—including potential misalignment.
Can LLMs simply tell us about unwanted behaviors they’ve picked up in training? We train a single Introspection Adapter (IA) that makes fine-tuned models describe their behaviors. It generalizes to detecting hidden misalignment, backdoors and safeguard removal.在 X 查看被引用的帖子
来源：Anthropic · x.com