OpenAI ↗ · 2025-06-18 18:00 · UTC+8
Toward understanding and preventing misalignment generalization
公司动态 OpenAI 原文语言:英文
We study how training on incorrect responses can cause broader misalignment in language models and identify an internal feature driving this behavior—one that can be reversed with minimal fine-tuning.
原文摘录
We study how training on incorrect responses can cause broader misalignment in language models and identify an internal feature driving this behavior—one that can be reversed with minimal fine-tuning.
以下是来源提供的简短摘录,完整内容请查看原文。