Dianyun Wang, Qingsen Ma, Yuhu Shang, Zhifeng Lu, Zhenbo Xu, Lechen Ning, Huijia Wu Beijing University of Posts and Telecommunications, Zhaofeng He Beijing University of Post and Telecommunication
Safety alignment—training large language models (LLMs) to refuse harmful requests while remaining helpful—is critical for responsible deployment. Prior work established that safety behaviors are governed by low-rank structures, suggesting parameter-efficient fine-tuning (PEFT) should be well-suited for alignment. However, Low-Rank Adaptation (LoRA) consistently underperforms full fine-tuning and reinforcement learning on safety benchmarks. We attribute this gap to semantic entanglement: safety-relevant directions are intertwined with unrelated concepts due to polysemanticity, impeding implicit subspace identification. To address this, we propose SAILS (Safety Alignment via Interpretable Low-rank Subspace), which leverages Sparse Autoencoders (SAEs) to disentangle representations into monosemantic features, constructs an interpretable safety subspace from SAE decoder directions, and uses it to initialize LoRA adapters. Theoretically, we prove that SAE-based identification achieves arbitrarily small recovery error under monosemanticity assumptions, while direct identification suffers an irreducible error floor. Empirically, SAILS achieves up to 99.6% safety rates across multiple model families and scales, exceeding full fine-tuning and matching RLHF-based models, with only 0.2% of parameters updated and providing interpretability.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Zixuan Zhou Beijing University of Posts and Telecommunications, Yujun Diao Beijing University of Post and Telecommunications, Zicheng Kong Beijing University of Posts and Telecommunications, Dehua Ma, Zhenbo Xu, Pei Pei Li, Zhaofeng He Beijing University of Post and Telecommunication
Large Language Models (LLMs) are primarily constrained by memory and bandwidth bottlenecks during deployment. Although Vector Quantization (VQ) has emerged as a promising solution, existing methods incur inference overhead due to massive codebook storage and intensive index lookups. Moreover, these methods typically suffer from non-negligible performance degradation under ultra-low bitwidth regimes. To bridge this gap, we propose Sparse-Compensated Vector Quantization (SCVQ), a novel framework designed for high-efficiency LLM vector quantization. SCVQ introduces a salience-aware weighted K-means clustering scheme with symmetry constraints to reduces codebook size and indexing costs. Central to our approach is a unified structured representation that consolidates outliers, salient weights, and quantization residuals into a single sparse compensation matrix. This design effectively preserves critical model information while leveraging VQ-specific properties to enable efficient custom kernels. Extensive experiments across multiple benchmarks demonstrate SCVQ’s superior performance. Specifically, SCVQ achieves a perplexity of 5.78 on WikiText-2 for LLaMA-2-7B at 2-bit quantization, while delivering a 1.4\times end-to-end inference speedup over existing baselines.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表