aifollow.news
返回 Rohan Paul
Rohan Paul· @rohanpaul_ai · X· · 原发布时间 AI 评分54

研究发现:模型能力测试的低分可被精确制造

AI 导读

一项研究用 LoRA 调整 Qwen 模型,使其在未见过的测试中取得接近目标的低分,误差在 1.9 分以内;仅靠提示词让模型表现变差,误差则达 42 至 47 分。不过,这种调整留下了异常痕迹:在选择题中,新增错误最多有 97% 集中在同一个选项字母上。研究提醒,评估危险能力时不能只看低分,还要检查模型错在哪里、错误如何分布。

原帖引用 · 原文

@rohanpaul_ai

This paper finds that a low benchmark score can be manufactured precisely, so a low score alone says little about what a model can do.

Safety tests often read a low score on a dangerous-capability probe as reassurance. But a low score can come from a model being held back, so the number alone proves little.

They trained a LoRA "dial" that pulls a Qwen model toward a smaller Qwen model, then compared its errors with the real small model's. They also tried prompting models to underperform, raising temperature, and adding weight noise.

The dial hit unseen target scores within 1.9 points, while prompting missed by 42 to 47 points. But on multiple choice, up to 97% of its new errors landed on 1 letter, a share no natural model in their pool approached.

Before reading a low score as low capability, check which items the model fails and how its wrong answers are spread.

来源:Rohan Paul · x.com

论文
发现内容有误?提交纠错