DF-RAG: Query-Aware Diversity for Retrieval-Augmented Generation

2026-01-23

AI Summary

This work addresses the limitations of traditional retrieval-augmented generation (RAG) in complex reasoning-based question answering, where redundant retrieval results often lead to insufficient information recall. To overcome this, the authors propose a query-aware diversity optimization mechanism that dynamically adjusts retrieval diversity for each query within the Maximal Marginal Relevance (MMR) framework. The approach balances relevance and informational complementarity without requiring additional fine-tuning or prior knowledge. Empirical evaluations demonstrate significant performance gains on reasoning-intensive QA tasks, with F1 scores improving by 4%–10% over conventional RAG across multiple benchmarks, achieving up to 91.3% of the theoretical performance upper bound.

Technology Category

• Natural Language Processing: Question Answering
• Search and Optimization: Metareasoning and Metaheuristics
• Data Mining & Knowledge Management: Intelligent Query Processing

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

Abstract

Retrieval-augmented generation (RAG) is a common technique for grounding language model outputs in domain-specific information. However, RAG is often challenged by reasoning-intensive question-answering (QA), since common retrieval methods like cosine similarity maximize relevance at the cost of introducing redundant content, which can reduce information recall. To address this, we introduce Diversity-Focused Retrieval-Augmented Generation (DF-RAG), which systematically incorporates diversity into the retrieval step to improve performance on complex, reasoning-intensive QA benchmarks. DF-RAG builds upon the Maximal Marginal Relevance framework to select information chunks that are both relevant to the query and maximally dissimilar from each other. A key innovation of DF-RAG is its ability to optimize the level of diversity for each query dynamically at test time without requiring any additional fine-tuning or prior information. We show that DF-RAG improves F1 performance on reasoning-intensive QA benchmarks by 4-10 percent over vanilla RAG using cosine similarity and also outperforms other established baselines. Furthermore, we estimate an Oracle ceiling of up to 18 percent absolute F1 gains over vanilla RAG, of which DF-RAG captures up to 91.3 percent.

Problem

• Retrieval-Augmented Generation
• reasoning-intensive QA
• redundant content
• information recall
• query-aware diversity

Innovation

• Diversity-Focused Retrieval
• Retrieval-Augmented Generation
• Maximal Marginal Relevance
• Reasoning-Intensive QA
• Query-Aware Diversity