DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrieval
This addresses the challenge of reasoning-intensive information retrieval for real-world applications, representing a strong specific gain but is incremental as it builds on existing retrieval-augmented generation methods.
The paper tackled the problem of retrieval-augmented generation struggling with abstract reasoning, analogical thinking, or multi-step inference in queries by presenting DIVER, a multi-stage retrieval pipeline, which achieved state-of-the-art nDCG@10 scores of 46.8 overall and 31.9 on original queries on the BRIGHT benchmark.
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.