论文60

论文发现基准低分可被精确制造,低分本身难以说明模型能力

原标题: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.

Rohan Paul@rohanpaul_ai发布时间 (北京时间)

一篇论文发现,基准测试的低分可以被精确制造,因此单看低分很难判断模型真实能力。研究者训练了一个 LoRA 调节器,把 Qwen 模型拉向更小的 Qwen 模型,其命中未见目标分数的误差在 1.9 分以内,而用提示词让模型故意表现不佳的误差为 42 到 47 分。

中文译文尚未完成,先为你展示原文。

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.

千问 Qwen安全对齐论文研究评测基准#论文/研究#安全/对齐#评测/基准