DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrieval

TL;DR

DIVER is a multi-stage retrieval pipeline designed to improve reasoning-intensive information retrieval by enhancing query understanding, employing reasoning-aware retrieval models, and sophisticated reranking, achieving state-of-the-art results on the BRIGHT benchmark.

Contribution

The paper introduces DIVER, a novel multi-stage retrieval system tailored for reasoning-intensive tasks, combining query expansion, reasoning-aware retrieval, and advanced reranking.

Findings

DIVER achieves state-of-the-art nDCG@10 scores of 46.8 overall.

It outperforms existing reasoning-aware models on the BRIGHT benchmark.

The approach effectively handles complex, reasoning-based queries.

Abstract

Retrieval-augmented generation has achieved strong performance on knowledge-intensive tasks where query-document relevance can be identified through direct lexical or semantic matches. However, many real-world queries involve abstract reasoning, analogical thinking, or multi-step inference, which existing retrievers often struggle to capture. To address this challenge, we present DIVER, a retrieval pipeline designed for reasoning-intensive information retrieval. It consists of four components. The document preprocessing stage enhances readability and preserves content by cleaning noisy texts and segmenting long documents. The query expansion stage leverages large language models to iteratively refine user queries with explicit reasoning and evidence from retrieved documents. The retrieval stage employs a model fine-tuned on synthetic data spanning medical and mathematical domains, along with hard negatives, enabling effective handling of reasoning-intensive queries. Finally, the reranking stage combines pointwise and listwise strategies to produce both fine-grained and globally consistent rankings. On the BRIGHT benchmark, DIVER achieves state-of-the-art nDCG@10 scores of 46.8 overall and 31.9 on original queries, consistently outperforming competitive reasoning-aware models. These results demonstrate the effectiveness of reasoning-aware retrieval strategies in complex real-world tasks.