# Memory-Aware and Uncertainty-Guided Retrieval for Multi-Hop Question Answering

arXiv: https://arxiv.org/abs/2503.23095 · HTML: https://mlsanity.com/paper/2503.23095/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 32 references that are in the map.
- First posted on arXiv 29 Mar 2025.

## Builds on (most cited first, 12 of 12)

- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies](https://mlsanity.com/paper/2101.02235/) (2021)
- [MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation](https://mlsanity.com/paper/2409.05591/) (2024)
- [IIRC: A Dataset of Incomplete Information Reading Comprehension Questions](https://mlsanity.com/paper/2011.07127/) (2020)
- [Bridging the Editing Gap in LLMs: FineEdit for Precise and Targeted Text Modifications](https://mlsanity.com/paper/2502.13358/) (2025)
- [CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control](https://mlsanity.com/paper/2405.18727/) (2024)
- [Graph Neural Network Enhanced Retrieval for Question Answering of LLMs](https://mlsanity.com/paper/2406.06572/) (2024)
- [Trajectory Tracking Using Frenet Coordinates with Deep Deterministic Policy Gradient](https://mlsanity.com/paper/2411.13885/) (2024)
- [Solving Situation Puzzles with Large Language Model and External Reformulation](https://mlsanity.com/paper/2503.18394/) (2025)

## Built on by (most cited first, 2 of 2)

- [Convomem Benchmark: Why Your First 150 Conversations Don't Need RAG](https://mlsanity.com/paper/2511.10523/) (2025)
- [PANINI-DR: Controlled Deep Research through Generative Semantic Workspaces](https://mlsanity.com/paper/2610.15208/) (2026)

## Abstract (arXiv)

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.