基于心智图景的检索增强生成技术提升长上下文理解能力

摘要

人类通过构建内容的整体语义表征来理解复杂长文本。这种全局视角有助于组织先验知识、解读新信息、整合散布于文档中的证据，心理学中揭示的"心智图景感知能力"正是如此。当前检索增强生成系统缺乏此类引导，因此在长上下文任务中表现不佳。本文提出心智图景感知RAG，这是首个为基于大语言模型的RAG系统赋予显式全局上下文感知能力的方法。该方法通过层级式摘要构建心智图景，并基于此全局语义表征指导检索与生成过程。这使得检索器能形成增强的查询嵌入，生成器能在连贯的全局上下文中对检索证据进行推理。我们在多个长上下文与双语基准测试中评估了该方法在证据理解和全局语义构建方面的表现。实验表明其持续超越基线模型，进一步分析显示该方法能将局部细节与连贯的全局表征对齐，实现更类人的长上下文检索与推理能力。

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.

基于心智图景的检索增强生成技术提升长上下文理解能力

Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding

摘要

Support