Tianyang Hu

Siquan Li, Kaiqi Jiang, Jiacheng Sun et al.

Despite the prevalence of the attention sink phenomenon in Large Language Models (LLMs), where initial tokens disproportionately monopolize attention scores, its structural origins remain elusive. This work provides a \textit{mechanistic explanation} for this phenomenon. First, we trace its root to the value aggregation process inherent in self-attention, which induces a systematic variance discrepancy. We further demonstrate that this discrepancy is drastically amplified by the activation of super neurons within Feed-Forward Network (FFN) layers. Specifically, the channel-sparse down-projections trigger a dimension disparity of the first-token representation, necessitating the formation of attention sinks as a structural anchor. Then, we validate this causal chain through two controlled interventions: (i) isolating the aggregation effect via attention mask modifications and (ii) amplifying the variance of targeted token representations. Both interventions can replicate attention sinks at arbitrary positions. Our mechanistic understanding offers a foundation for the systematic control of sink formation. Finally, as a proof of concept, we propose \textit{head-wise RMSNorm}, an architectural modification that stabilizes value aggregation outputs during pre-training. Our experiments demonstrate that restoring statistical parity across positions significantly accelerates convergence.

Siquan Li, Yao Tong, Haonan Wang et al.

Transformers underpin modern large language models (LLMs) and are commonly assumed to be behaviorally unstructured at random initialization, with all meaningful preferences emerging only through large-scale training. We challenge this assumption by showing that randomly initialized transformers already exhibit strong and systematic structural biases. In particular, untrained models display extreme token preferences: across random input sequences, certain tokens are predicted with probabilities orders of magnitude larger. We provide a mechanistic explanation for this phenomenon by dissecting the transformer architecture at initialization. We show that extreme token preference arises from a contraction of token representations along a random seed-dependent direction. This contraction is driven by two interacting forces: (i) asymmetric nonlinear activations in MLP sublayers induce global (inter-sequence) representation concentration, and (ii) self-attention further amplifies this effect through local (intra-sequence) aggregation. Together, these mechanisms align hidden representations along a direction determined solely by the random initialization, producing highly non-uniform next-token predictions. Beyond mechanistic insight, we demonstrate that these initialization-induced biases persist throughout training, forming a stable and intrinsic model identity. Leveraging this property, we introduce SeedPrint, a fingerprinting method that can reliably distinguish models that differ only in their random initialization, even after extensive training and under substantial distribution shift. Finally, we identify a fundamental positional discrepancy inherent to the attention mechanism's intra-sequence contraction that is causally linked to the attention-sink phenomenon. This discovery provides a principled explanation for the emergence of sinks and offers a pathway for their control.

Yichen Xu, Yuyang Liang, Shan Dai et al.

As large language models (LLMs) continue to grow, the cost of full-parameter fine-tuning has made parameter-efficient fine-tuning (PEFT) the default strategy for downstream adaptation. Constraints from inference latency in scalable serving and fine-tuning cost in edge or rapid-deployment settings make the choice of which layers to fine-tune unavoidable. Yet current practice typically applies PEFT uniformly across all layers, with limited understanding or leverage of layer selection. This paper develops a unified projected residual view of PEFT on top of a frozen base model. Under a local quadratic approximation, layerwise adaptation is governed by three quantities: (i) the projected residual norm (resnorm), which measures how much correctable bias a layer can capture; (ii) the activation energy, which determines feature conditioning; and (iii) layer coupling, which quantifies how strongly residuals interact across layers. We show that, for squared loss and linear adapters, the resnorm equals a normalized gradient norm, activation energy controls ill-conditioning and noise amplification, and weak coupling yields approximately additive layerwise contributions. Building on these insights, we introduce the Layer Card, a reusable diagnostic that summarizes residual signal strength, compute cost, and performance for each layer of a given model. With an identical model and LoRA configuration, Layer Card-guided placement refines the choice of adapted layers to flexibly prioritize different objectives, such as maximizing performance or reducing fine-tuning cost. Moreover, on Qwen3-8B, we show that selectively adapting a subset of layers can achieve performance close to full-layer LoRA while substantially reducing fine-tuning cost and the number of adapter-augmented layers during inference, offering a more cost-performance-aware alternative to full-layer insertion.