arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.08504cs.CL
收藏

一层解释所有:理解大语言模型中大规模激活现象

A Single Layer to Explain Them All:Understanding Massive Activations in Large Language Models

Rutgers University(罗格斯大学);Wake Forest University(威克森林大学);Meta AI

Zeru Shi, Zhenting Wang, Fan Yang, Qifan Wang, Ruixiang Tang

AI总结:

研究大语言模型中大规模激活的起源,发现ME层是大规模激活首次出现的层,并提出方法减少大规模激活的刚性,提升模型性能。

摘要:

我们研究了大语言模型(LLMs)中大规模激活的起源,并识别出一个特定的层,称为大规模涌现层(ME Layer),该层在不同模型家族中一致出现,大规模激活首次在此层产生并通过残差连接传播到更深层。我们显示,在ME层中,RMSNorm和FFN参数共同促进了大规模激活的出现。一旦形成,大规模激活标记表示在各层中保持基本不变,减少传递到注意力模块的隐藏表示多样性。受此限制启发,我们提出了一种简单有效的减少大规模激活标记刚性的方法。该方法在多个任务上提高了LLM性能,包括指令跟随和数学推理,在无训练和微调设置中均有效。此外,我们显示该方法通过选择性削弱注意力沉底,揭示了其在隐藏状态层面的起源,并为原理性缓解策略提供了新见解。

英文摘要:

We investigate the origins of massive activations in large language models (LLMs) and identify a specific layer named the \textbf{Massive Emergence Layer (ME Layer)}, that is consistently observed across model families, where massive activations first emerge and subsequently propagate to deeper layers through residual connections. We show that, within the ME Layer both the RMSNorm and the FFN parameters jointly contribute to the emergence of massive activations. Once formed, the massive activation token representation remains largely invariant across layers, reducing the diversity of hidden representations passed to the attention module. Motivated by this limitation, we propose a simple and effective method to reduce the rigidity of the massive activation token. Our approach consistently improves LLM performance across multiple tasks, including instruction following and math reasoning, in both training free and fine tuning settings. Moreover, we show that our method mitigates attention sinks by selectively weakening their influence, elucidating their origin at the hidden state level and shedding new light on principled mitigation strategies.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑