返回首页
Towards Data Science··行业媒体

Same Answer, Different Reason: What a Reasoning Model Says When It Follows a Planted Hint

中文摘要

研究发现,AI模型被植入错误提示后,会给出相同错误答案,但会生成不同且有缺陷的推理来论证。

English Summary

A study found AI models, when given planted wrong hints, produce the same incorrect answer but generate different, often flawed, reasoning to justify it.

原文节选

I put wrong answers in front of 200 exam questions and read what a small model’s reasoning said when it fell for them.