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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ji, Yuelyu, Meng, Rui, Li, Zhuochun, He, Daqing
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916665889914880
author Ji, Yuelyu
Meng, Rui
Li, Zhuochun
He, Daqing
author_facet Ji, Yuelyu
Meng, Rui
Li, Zhuochun
He, Daqing
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_23095
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Memory-Aware and Uncertainty-Guided Retrieval for Multi-Hop Question Answering
Ji, Yuelyu
Meng, Rui
Li, Zhuochun
He, Daqing
Computation and Language
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.
title Memory-Aware and Uncertainty-Guided Retrieval for Multi-Hop Question Answering
topic Computation and Language
url https://arxiv.org/abs/2503.23095