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

arXiv: https://arxiv.org/abs/2601.17212 · HTML: https://mlsanity.com/paper/2601.17212/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation.
- Builds on 28 of its 44 references that are in the map.
- First posted on arXiv 23 Jan 2026.

## Placed in

- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)

## Builds on (most cited first, 28 of 28)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Large Language Models Struggle to Learn Long-Tail Knowledge](https://mlsanity.com/paper/2211.08411/) (2022)
- [∞Bench: Extending Long Context Evaluation Beyond 100K Tokens](https://mlsanity.com/paper/2402.13718/) (2024)
- [Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval](https://mlsanity.com/paper/2009.12756/) (2020)
- [Multi-hop Reading Comprehension through Question Decomposition and Rescoring](https://mlsanity.com/paper/1906.02916/) (2019)
- [Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach](https://mlsanity.com/paper/2407.16833/) (2024)
- [Thinkless: LLM Learns When to Think](https://mlsanity.com/paper/2505.13379/) (2025)
- [Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning](https://mlsanity.com/paper/2505.17813/) (2025)
- [Hierarchical Graph Network for Multi-hop Question Answering](https://mlsanity.com/paper/1911.03631/) (2019)
- [StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization](https://mlsanity.com/paper/2410.08815/) (2024)
- [Cognitive Graph for Multi-Hop Reading Comprehension at Scale](https://mlsanity.com/paper/1905.05460/) (2019)
- [Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval](https://mlsanity.com/paper/2101.00436/) (2021)
- [LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering](https://mlsanity.com/paper/2410.18050/) (2024)
- [Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking](https://mlsanity.com/paper/2310.13243/) (2023)
- [How Much Can RAG Help the Reasoning of LLM?](https://mlsanity.com/paper/2410.02338/) (2024)
- [Grounding Language Model with Chunking-Free In-Context Retrieval](https://mlsanity.com/paper/2402.09760/) (2024)
- [Leveraging Structured Information for Explainable Multi-hop Question Answering and Reasoning](https://mlsanity.com/paper/2311.03734/) (2023)
- [BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering](https://mlsanity.com/paper/1904.04969/) (2019)
- [Exploiting Reasoning Chains for Multi-hop Science Question Answering](https://mlsanity.com/paper/2109.02905/) (2021)
- [GenDec: A robust generative Question-decomposition method for Multi-hop reasoning](https://mlsanity.com/paper/2402.11166/) (2024)
- [Diversity Enhances an LLM's Performance in RAG and Long-context Task](https://mlsanity.com/paper/2502.09017/) (2025)
- [Answering Any-hop Open-domain Questions with Iterative Document Reranking](https://mlsanity.com/paper/2009.07465/) (2020)

## Built on by (most cited first, 5 of 5)

- [Principled and Scalable Diversity-Aware Retrieval via Cardinality-Constrained Binary Quadratic Programming](https://mlsanity.com/paper/2604.02554/) (2026)
- [DIVERGE: Diversity-Enhanced RAG for Open-Ended Information Seeking](https://mlsanity.com/paper/2602.00238/) (2026)
- [SkillPager: Query-Adaptive Intra-Skill Navigation via Semantic Node Retrieval](https://mlsanity.com/paper/2606.00822/) (2026)
- [MORSE: Multi-Context Ordering via Reverse Scoring for Evidence-Preserving Compression](https://mlsanity.com/paper/2609.27380/) (2026)
- [Cross-Protocol Personality Assessment with LLMs: Aligning Behavioral Evidence with Human Ratings](https://mlsanity.com/paper/2610.16050/) (2026)

## Abstract (arXiv)

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.