mlsanityData to 13 Oct 2026

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

arXiv 2503.23095 ↗First posted 29 Mar 2025cs.CLcited by 1

Not on the map. Why?

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.

Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 12 of its 32 references that are in the map. First posted on arXiv 29 Mar 2025.

Builds on

12 of 32 references.

References · 12

  1. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,716
  2. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,433
  3. 2021Improving language models by retrieving from trillions of tokenscited by 1,286
  4. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,266
  5. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 738
  6. 2024MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentationcited by 119
  7. 2020IIRC: A Dataset of Incomplete Information Reading Comprehension Questionscited by 52
  8. 2025Bridging the Editing Gap in LLMs: FineEdit for Precise and Targeted Text Modificationscited by 21
  9. 2024CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Controlcited by 13
  10. 2024Graph Neural Network Enhanced Retrieval for Question Answering of LLMscited by 10
  11. 2024Trajectory Tracking Using Frenet Coordinates with Deep Deterministic Policy Gradientcited by 7
  12. 2025Solving Situation Puzzles with Large Language Model and External Reformulationcited by 3

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Convomem Benchmark: Why Your First 150 Conversations Don't Need RAGcited by 10

Similar, not cited

Close in wording, no citation either way

  1. 2026Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering
  2. 2026STRIDE: Strategic Iterative Decision-Making for Retrieval-Augmented Multi-Hop Question Answering
  3. 2024Review-Then-Refine: A Dynamic Framework for Multi-Hop Question Answering with Temporal Adaptability
  4. 2025A Comprehensive Evaluation of Transformer-Based Question Answering Models and RAG-Enhanced Design
  5. 2026PAR2-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering
  6. 2025Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answering
  7. 2026BridgeRAG: Training-Free Bridge-Conditioned Retrieval for Multi-Hop Question Answering
  8. 2026Retrieval--Reasoning Processes for Multi-hop Question Answering: A Four-Axis Design Framework and Empirical Trends