2026· Annual Meeting of the Association for Computational Linguistics· pp. 1028-1044· 0 citations· 34 references
Computer Science
TL;DR
This paper introduces RoPE-based Block-wise Sparse Attention (RoBSA), a method designed specifically for MLA during the decoding stage of model inference that significantly reduces end-to-end inference latency in the decoding stage by up to 2 .
Abstract
Large Language Models (LLMs) have rapidly advanced in recent years, scaling up in both parameter count and context length. However, as context windows extend from thousands to hundreds of thousands of tokens, attention computation becomes the dominant source of memory usage and runtime in decoding stages, severely limiting the efficiency and scalability of long-context LLMs. Sparse attention has emerged as a promising solution, reducing complexity by computing attention over only a subset of context tokens. However, the sparse attention for Multi-head Latent Attention (MLA) which is a variant of standard MHA is rarely studied. In this paper, we introduce RoPE-based Block-wise Sparse Attention (RoBSA), a method designed specifically for MLA during the decoding stage of model inference. RoBSA leverages the decoupled nature of RoPE within MLA to implement token selection in a blockwise manner. RoBSA is a lightweight, training-free, and layer-aware algorithm that can be integrated in a plug-and-play fashion. Our method significantly reduces end-to-end inference latency in the decoding stage by up to 2 . 55 × with minimal accuracy loss compared to full attention in long-context scenarios for very large models.
Hierarchical Landmark Sparse Attention is proposed, a chunk-wise sparse attention mechanism that learns chunk selection end-to-end under the language-modeling (LM) loss, enabling long-context LLMs that are both more efficient and more effective on general long-context tasks than their full-attention counterparts.
Block-sparse attention scales long-context language models by replacing the O(N^2) softmax with a per-query top-k selection over key blocks. This cutoff is myopic: when the k-th and (k+1)-th blocks are nearly tied in score, the selector commits without spending extra budget, and a dropped block carrying answer evidence is unrecoverable downstream. We propose a value-of-information router that measures, for each query, how decisively the top-k cut was made, and doubles the kept set for the queries where that gap is smallest; the rule is backbone-agnostic and stacks with existing block-scoring methods such as Quest. On LongBench-v2 medium at n=215 (the entire dataset subset), router-on-Quest reaches paired recall 0.75 vs. top-k 0.47 -- +28 pp over the SSA-style baseline (McNemar p<0.01) -- and lands within 2 pp of dense on RULER NIAH multikey at the same context. The lift reproduces on four models from three architectures (Qwen2.5, Mistral-Nemo, Qwen3.6). At 128K, the router preserves 0.81 and 0.89 of dense accuracy on Qwen2.5-7B-1M and Qwen3.6 (vs. SSA-style top-k at 0.09 on the former) while the fused selection-plus-kernel pipeline runs at 0.62x and 0.80x dense wall time.
Pruning is essential for the efficient deployment of Large Language Models (LLMs); however, it causes severe performance degradation due to the structural distortion induced by sparsity. Existing recovery strategies, such as LoRA, predominantly employ global fine-tuning, often overlooking the mechanistic root of this degradation: the layer-wise accumulation and amplification of local errors. To address this limitation, we propose LaCo ( La yer-wise Co mpensation), a framework that reori-ents the recovery paradigm from global adaptation to hierarchical representation alignment. By sequentially optimizing each layer to re-construct the model’s hidden states, LaCo effectively intercepts the error propagation chain at its source. Extensive experiments demonstrate that LaCo surpasses parameter-efficient baselines in both perplexity reduction and zero-shot reasoning. Notably, it reduces recovery-time memory usage to approximately 1 / 7 of the baseline and requires only 2,048 unlabeled samples to match a LoRA model trained on 50k examples—achieving a ∼ 25 × improvement in data efficiency.
Yingen Liu, Fan Wu, Xuyan Pan et al.· Annual Meeting of the Associ...· 0 citations
This work presents the first comprehensive mechanistic interpretability study of MLA, training a 114M-parameter transformer and analyzing its representations through SVD, attention head taxonomy, linear probing, and a disruption-attribution analysis.
S. Dhruvil, Fenil Sojitra, R. Chauhan· 0 citations
CoSA is proposed, a two-stage training-free Sparse Attention under proxy-kernel CO-design, which couples a Kernel-Aware Proxy (KAP) with an Ordered-Skipping Kernel (OSK) and achieves a 4.93% attention speedup and reduces end-to-end Time-to-First-Token by 2.53% with negligible performance degradation.
Experiments on diverse open-source text classification datasets show that AHR can outperform standard baselines like LoRA when learning from limited samples, despite having 200-1000x fewer trainable parameters, as the authors' AHR only modifies ~0.0001% of the model's parameters.
Tuomas P. Oikarinen, Zixiao Chen, Charlotte Siska et al.· 0 citations