Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answering

TL;DR

Q-DREAM enhances multi-hop question answering by decomposing questions, modeling subquestion dependencies, and dynamically aligning passages, leading to improved accuracy and efficiency over existing retrieval-augmented methods.

Contribution

The paper introduces Q-DREAM, a novel framework with modules for question decomposition, dependency modeling, and dynamic retrieval, advancing multi-hop QA performance.

Findings

Achieves state-of-the-art results on multiple benchmarks.

Improves retrieval efficiency while maintaining high accuracy.

Effectively models subquestion dependencies for better understanding.

Abstract

Retrieval-augmented generation (RAG) is usually integrated into large language models (LLMs) to mitigate hallucinations and knowledge obsolescence. Whereas,conventional one-step retrieve-and-read methods are insufficient for multi-hop question answering, facing challenges of retrieval semantic mismatching and the high cost in handling interdependent subquestions. In this paper, we propose Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answering (Q-DREAM). Q-DREAM consists of three key modules: (1) the Question Decomposition Module (QDM), which decomposes multi-hop questions into fine-grained subquestions; (2) the Subquestion Dependency Optimizer Module (SDOM), which models the interdependent relations of subquestions for better understanding; and (3) the Dynamic Passage Retrieval Module (DPRM), which aligns subquestions with relevant passages by optimizing the semantic embeddings. Experimental results across various benchmarks demonstrate that Q-DREAM significantly outperforms existing RAG methods, achieving state-of-the-art performance in both in-domain and out-of-domain settings. Notably, Q-DREAM also improves retrieval efficiency while maintaining high accuracy compared with recent baselines.