MiA-Signature：用於長文本理解的全局激活近似方法

MiA-Signature: Approximating Global Activation for Long-Context Understanding

May 7, 2026

作者: Yuqing Li, Jiangnan Li, Mo Yu, Zheng Lin, Weiping Wang, Jie Zhou

cs.AI

摘要

認知科學研究日益表明，可報告的意識存取與分佈式記憶系統的全局激發相關，但這種激活僅能部分獲取，因為個體無法直接存取或枚舉所有被激活的內容。這種張力揭示了一種合理機制：認知可能依賴於一種壓縮表徵，用以近似模擬激活對下游處理的全局影響。受此啟發，我們提出「心智景觀激活特徵」的概念，即由查詢誘導的全局激活模式的壓縮表徵。在大型語言模型系統中，此概念通過基於子模函數的高層概念選擇來實現，這些概念能覆蓋被激活的語境空間，並可選地通過工作記憶進行輕量級迭代更新來精煉。最終產生的心智景觀激活特徵作為條件信號，既能近似完整激活狀態的效果，又保持計算上的可處理性。將心智景觀激活特徵整合至檢索增強生成和智能體系統後，在多項長上下文理解任務中均實現了持續的性能提升。

English

A growing body of work in cognitive science suggests that reportable conscious access is associated with global ignition over distributed memory systems, while such activation is only partially accessible as individuals cannot directly access or enumerate all activated contents. This tension suggests a plausible mechanism that cognition may rely on a compact representation that approximates the global influence of activation on downstream processing. Inspired by this idea, we introduce the concept of Mindscape Activation Signature (MiA-Signature), a compressed representation of the global activation pattern induced by a query. In LLM systems, this is instantiated via submodular-based selection of high-level concepts that cover the activated context space, optionally refined through lightweight iterative updates using working memory. The resulting MiA-Signature serves as a conditioning signal that approximates the effect of the full activation state while remaining computationally tractable. Integrating MiA-Signatures into both RAG and agentic systems yields consistent performance gains across multiple long-context understanding tasks.