# Masking or Mitigating? Deconstructing the Impact of Query Rewriting on Retriever Biases in RAG

arXiv: https://arxiv.org/abs/2604.06097 · HTML: https://mlsanity.com/paper/2604.06097/

## Key facts

- No citing papers in the map yet (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 41 references that are in the map.
- First posted on arXiv 7 Apr 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)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction](https://mlsanity.com/paper/2112.01488/) (2021)
- [Evaluating Verifiability in Generative Search Engines](https://mlsanity.com/paper/2304.09848/) (2023)
- [RAFT: Adapting Language Model to Domain Specific RAG](https://mlsanity.com/paper/2403.10131/) (2024)
- [ReACC: A Retrieval-Augmented Code Completion Framework](https://mlsanity.com/paper/2203.07722/) (2022)
- [RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder](https://mlsanity.com/paper/2205.12035/) (2022)
- [How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval](https://mlsanity.com/paper/2302.07452/) (2023)
- [Reliable, Adaptable, and Attributable Language Models with Retrieval](https://mlsanity.com/paper/2403.03187/) (2024)
- [Revisiting DocRED -- Addressing the False Negative Problem in Relation Extraction](https://mlsanity.com/paper/2205.12696/) (2022)
- [RaFe: Ranking Feedback Improves Query Rewriting for RAG](https://mlsanity.com/paper/2405.14431/) (2024)
- [Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model](https://mlsanity.com/paper/2212.09146/) (2022)
- [What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary](https://mlsanity.com/paper/2212.10380/) (2022)
- [SLM-Mod: Small Language Models Surpass LLMs at Content Moderation](https://mlsanity.com/paper/2410.13155/) (2024)
- [Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual Evidence](https://mlsanity.com/paper/2503.05037/) (2025)
- [Dwell in the Beginning: How Language Models Embed Long Documents for Dense Retrieval](https://mlsanity.com/paper/2404.04163/) (2024)
- [MoMoE: Mixture of Moderation Experts Framework for AI-Assisted Online Governance](https://mlsanity.com/paper/2505.14483/) (2025)
- [EnronQA: Towards Personalized RAG over Private Documents](https://mlsanity.com/paper/2505.00263/) (2025)
- [GuRE:Generative Query REwriter for Legal Passage Retrieval](https://mlsanity.com/paper/2505.12950/) (2025)
- [PIR-RAG: A System for Private Information Retrieval in Retrieval-Augmented Generation](https://mlsanity.com/paper/2509.21325/) (2025)
- [The Hidden Toll of Social Media News: Causal Effects on Psychosocial Wellbeing](https://mlsanity.com/paper/2601.13487/) (2026)
- [Detecting Early and Implicit Suicidal Ideation via Longitudinal and Information Environment Signals on Social Media](https://mlsanity.com/paper/2510.14889/) (2025)
- [VASTU: Language Models Struggle to Recognize Online Community Values](https://mlsanity.com/paper/2601.12491/) (2026)
- [Answer Bubbles: Information Exposure in AI-Mediated Search](https://mlsanity.com/paper/2603.16138/) (2026)
- [Does Reasoning Make Search More Fair? Comparing Fairness in Reasoning and Non-Reasoning Rerankers](https://mlsanity.com/paper/2603.10332/) (2026)

## Abstract (arXiv)

Dense retrievers in retrieval-augmented generation (RAG) systems exhibit systematic biases -- including brevity, position, literal matching, and repetition biases -- that can compromise retrieval quality. Query rewriting techniques are now standard in RAG pipelines, yet their impact on these biases remains unexplored. We present the first systematic study of how query enhancement techniques affect dense retrieval biases, evaluating five methods across six retrievers. Our findings reveal that simple LLM-based rewriting achieves the strongest aggregate bias reduction (54%), yet fails under adversarial conditions where multiple biases combine. Mechanistic analysis uncovers two distinct mechanisms: simple rewriting reduces bias through increased score variance, while pseudo-document generation methods achieve reduction through genuine decorrelation from bias-inducing features. However, no technique uniformly addresses all biases, and effects vary substantially across retrievers. Our results provide practical guidance for selecting query enhancement strategies based on specific bias vulnerabilities. More broadly, we establish a taxonomy distinguishing query-document interaction biases from document encoding biases, clarifying the limits of query-side interventions for debiasing RAG systems.