Lingrui Mei, Shenghua Liu Institute of Computing Technology, Chinese Academy of Sciences, Yiwei Wang University of California, Merced, Yuyao Ge, Baolong Bi, Jiayu Yao, Jun Wan UBS Group AG, Ziling Yin 等 10 位作者
Long contexts break transformers: attention scores dilute across thousands of tokens, critical information gets lost in the middle, and the model cannot adapt to novel patterns at inference time. Recent work on test-time adaptation addresses this by maintaining a form of working memory—transient parameters updated on the current context—but existing approaches employ uniform write policies that waste computation on low-value regions and suffer from high gradient variance across semantically heterogeneous contexts. In this work, we reframe test-time adaptation as a budget-constrained memory consolidation problem, asking: given limited computational budget, which parts of the context should be consolidated into working memory? We propose GDWM (\textbf{G}ated \textbf{D}ifferentiable \textbf{W}orking \textbf{M}emory), a framework that introduces a Write Controller to gate the memory consolidation process. Our controller estimates Contextual Utility—an information-theoretic measure quantifying how much each region depends on long-range context—and allocates gradient steps accordingly, subject to a coverage constraint that ensures global representation. Theoretically, we prove that our chunk-restricted sampling strategy reduces gradient variance by eliminating inter-chunk variance via the Law of Total Variance. Experiments on ZeroSCROLLS and LongBench v2 benchmarks demonstrate that GDWM achieves comparable or superior performance with 4 ×fewer gradient steps compared to uniform baselines—excelling on sparse-information tasks (+6–13% on Qasper, +5–13% on GovReport for smaller models) while revealing principled trade-offs on dense-coverage tasks, establishing a new efficiency-performance Pareto frontier for test-time adaptation.
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
Lingrui Mei, Shenghua Liu Institute of Computing Technology, Chinese Academy of Sciences, Yiwei Wang University of California, Merced, Baolong Bi, Ruibin Yuan, Xueqi Cheng Institute of Computing Technology, Chinese Academy
As Large Language Models (LLMs) grow increasingly powerful, ensuring their safety and alignment with human values remains a critical challenge. Current alignment approaches predominantly rely on refusal alignment, such as training models to refuse harmful prompts or implementing filters at various stages to block certain responses. These methods are designed toward a binary outcome: either denying to answer the question entirely or answering with full access to the model’s parametric knowledge. The binary nature of current alignment approaches presents significant limitations. These methods often fail to balance safety and utility, resulting in either overly cautious responses or overlooking subtle harmful content. They also prevent users from accessing benign information when it’s mixed with harmful content. For instance, a model might refuse to provide basic, public information about a medication’s composition due to misuse concerns. Furthermore, these approaches struggle with context-dependent sensitivity, potentially over-censoring harmless content or missing nuanced harmful outputs. Ideally, LLMs should offer informative responses while avoiding the disclosure of harmful and sensitive information. To address these challenges, we introduce HiddenGuard, a novel framework for fine-grained safe generation in LLMs. Our method incorporates PRISM (rePresentation Router for In-Stream Moderation), a specialized moudule that operates alongside the LLM architecture. By leveraging intermediate hidden states, HiddenGuard enables real-time, token-level harmfulness detection and redaction, without loss in capability. This approach captures deeper semantic information, allowing for more nuanced and context-aware content control compared to traditional filtering techniques. Consequently, the model can generate informative responses while selectively redacting or replacing sensitive information, rather than refusing to answer outright. We also contribute a comprehensive dataset with token-level fine-grained annotations of potentially harmful information across diverse contexts. Our experiments demonstrate that HiddenGuard achieves over 90% in F1 score for detecting and redacting harmful content while preserving the overall utility and informativeness of the model’s responses.
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