Query, Decompose, Compress: Structured Query Expansion for Efficient Multi-Hop Retrieval

TL;DR

DeCoR introduces a structured approach to multi-hop retrieval by decomposing queries and compressing evidence, improving efficiency and accuracy without relying on large generative models.

Contribution

The paper presents DeCoR, a novel framework that restructures reasoning and synthesizes evidence, outperforming larger models in multi-hop retrieval tasks.

Findings

DeCoR outperforms strong baselines with smaller LLMs.

Structured query decomposition enhances retrieval robustness.

Summarization of dispersed evidence improves relevance.

Abstract

Large Language Models (LLMs) have been increasingly employed for query expansion. However, their generative nature often undermines performance on complex multi-hop retrieval tasks by introducing irrelevant or noisy information. To address this challenge, we propose DeCoR (Decompose and Compress for Retrieval), a framework grounded in structured information refinement. Rather than generating additional content, DeCoR strategically restructures the query's underlying reasoning process and distills supporting evidence from retrieved documents. It consists of two core components tailored to the challenges of multi-hop retrieval: (1) Query Decomposition, which decomposes a complex query into explicit reasoning steps, and (2) Query-aware Document Compression, which synthesizes dispersed evidence from candidate documents into a concise summary relevant to the query. This structured design ensures that the final query representation remains both robust and comprehensive. Experimental results demonstrate that, despite utilizing a relatively small LLM, DeCoR outperforms strong baselines that rely on larger models. This finding underscores that, in complex retrieval scenarios, sophisticatedly leveraging the reasoning and summarization capabilities of LLMs offers a more efficient and effective solution than relying solely on their generative capability.