动态触发检索，让模型更智能地找证据并记住关键信息。
Memory-Aware and Uncertainty-Guided Retrieval for Multi-Hop Question Answering
- 用提示词提取关键实体，判断何时该检索
- 根据注意力和熵值动态决定是否检索，减少冗余
- 保留高置信度事实，确保多步推理一致
多跳问答需要模型从多个证据中检索并推理。尽管检索增强生成（RAG）已取得进展，现有方法仍存在两大问题：（1）检索步骤固定或过于频繁；（2）未能有效利用之前检索到的知识。我们提出 MIND（Memory-Informed and Interactive Dynamic RAG）框架，通过三种机制解决：（i）基于提示的实体抽取以识别推理相关元素；（ii）基于标记级熵和注意力信号的动态检索触发；（iii）记忆感知过滤，将高置信度事实跨推理步骤存储，实现一致的多跳生成。
原文摘要 · Abstract (English)
Multi-hop question answering (QA) requires models to retrieve and reason over multiple pieces of evidence. While Retrieval-Augmented Generation (RAG) has made progress in this area, existing methods often suffer from two key limitations: (1) fixed or overly frequent retrieval steps, and (2) ineffective use of previously retrieved knowledge. We propose MIND (Memory-Informed and INteractive Dynamic RAG), a framework that addresses these challenges through: (i) prompt-based entity extraction to identify reasoning-relevant elements, (ii) dynamic retrieval triggering based on token-level entropy and attention signals, and (iii) memory-aware filtering, which stores high-confidence facts across reasoning steps to enable consistent multi-hop generation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。