arXiv cs.AI· Fan Yang, Yue Song·· 3 天前AI 评分23
注意力汇形成前的隐藏状态几何：arXiv 研究揭示并调控其形成过程
Before Attention Sinks Form: Hidden-State Geometry Reveals and Modulates Their Formation
AI 导读
一项 arXiv 研究在注意力汇形成前约两到三层处发现隐藏状态的短程谱重组信号，该信号在 Qwen2.5、GLM-Z1 和 GPT-OSS 中均可预测后续汇的形成。研究者仅修改当前注意力计算后隐藏状态的奇异值，即可相对范数匹配的随机谱扰动改变后续汇行为；在 Qwen2.5 中，抑制效应伴随下一层对位置 0 的 query-key 偏好下降。
正文 · 原文
Abstract:Attention sinks are usually studied after they have formed. We ask whether a measurable hidden-state change appears beforehand and whether changing that geometry alters what happens later. To remove network depth as a shortcut, we compare prompts in the same model and at the same layer. When sink timing varies across prompts, simple spectral summaries of the hidden states add information beyond current attention, with the clearest prompt-specific signal in a short window about two to three layers before sink formation. The predictive strength varies across cohorts, so we treat the spectrum as a readout of a pre-sink state change rather than a universal warning statistic. The signal is broader than one measured extreme activation. We then modify only the singular values of the post-layer hidden states after current attention has already been computed. These interventions change later sink behavior in Qwen2.5, GLM-Z1, and GPT-OSS relative to norm-matched random spectral perturbations. In Qwen2.5, the immediate suppressive effect is accompanied by a reduction in next-layer query--key preference for position~0, and the learned spectral directions remain stable when estimated from substantially less training data. Together, the results show that attention sinks are preceded by a short spectral reorganization of hidden states, and directly perturbing this geometry can causally alter subsequent sink formation.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.16745 [cs.LG] |
| (or arXiv:2610.16745v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.16745 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Fan Yang [view email]
[v1]
Mon, 12 Oct 2026 13:14:10 UTC (444 KB)
来源：arXiv cs.AI · arxiv.org