基於心智圖景感知的檢索增強生成技術：提升長上下文理解能力

摘要

人類理解長篇複雜文本時，依賴的是對內容的整體語義表徵。心理學研究揭示的「心智景觀感知能力」表明，這種全域視角有助於組織先備知識、解讀新資訊，並整合分散在文件各處的證據。現有的檢索增強生成系統因缺乏此種引導機制，在處理長上下文任務時表現不佳。本文提出首個具備顯式全域上下文感知能力的LLM檢索增強生成方法——心智景觀感知RAG。該方法透過階層式摘要構建心智景觀，並以此全域語義表徵為基礎協調檢索與生成過程：使檢索器能形成富含語境信息的查詢嵌入，同時讓生成器能在連貫的全域上下文框架中對檢索證據進行推理。我們在多樣化的長上下文及雙語基準測試中評估該方法在證據推理與全域語義建構方面的表現。實驗結果顯示其持續超越基準模型，進一步分析表明該方法能將局部細節與連貫的全域表徵相結合，實現更類人的長上下文檢索與推理能力。

English

Humans understand long and complex texts by relying on a holistic semantic representation of the content. This global view helps organize prior knowledge, interpret new information, and integrate evidence dispersed across a document, as revealed by the Mindscape-Aware Capability of humans in psychology. Current Retrieval-Augmented Generation (RAG) systems lack such guidance and therefore struggle with long-context tasks. In this paper, we propose Mindscape-Aware RAG (MiA-RAG), the first approach that equips LLM-based RAG systems with explicit global context awareness. MiA-RAG builds a mindscape through hierarchical summarization and conditions both retrieval and generation on this global semantic representation. This enables the retriever to form enriched query embeddings and the generator to reason over retrieved evidence within a coherent global context. We evaluate MiA-RAG across diverse long-context and bilingual benchmarks for evidence-based understanding and global sense-making. It consistently surpasses baselines, and further analysis shows that it aligns local details with a coherent global representation, enabling more human-like long-context retrieval and reasoning.

基於心智圖景感知的檢索增強生成技術：提升長上下文理解能力

Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding

摘要

Support