Lune

ACL Findings2026

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

Agam Goyal, Koyel Mukherjee, Apoorv Saxena, Anirudh Phukan, Eshwar Chandrasekharan, Hari Sundaram

Abstract

Dense retrievers in retrieval-augmented generation (RAG) systems exhibit systematic biasesincluding 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 LLMbased 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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Precise Zero-Shot Dense Retrieval without Relevance Labels cites Dense Passage Retrieval for Open-Domain Question Answering
  • ReACC: A Retrieval-Augmented Code Completion Framework cites Dense Passage Retrieval for Open-Domain Question Answering
  • Query Rewriting in Retrieval-Augmented Large Language Models cites Dense Passage Retrieval for Open-Domain Question Answering
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on13

  1. Precise Zero-Shot Dense Retrieval without Relevance LabelsLuyu Gao, Xueguang Ma, Jimmy Lin, Jamie CallanACL 2023 · 211 citations
  2. ReACC: A Retrieval-Augmented Code Completion FrameworkShuai Lu, Nan Duan, Hojae Han, Daya Guo et al.ACL 2022 · 208 citations
  3. Query Rewriting in Retrieval-Augmented Large Language ModelsXinbei Ma, Yeyun Gong, Pengcheng He, Hai Zhao et al.EMNLP 2023 · 191 citations
  4. Evaluating Verifiability in Generative Search EnginesNelson F. Liu, Tianyi Zhang, Percy LiangEMNLP Findings 2023 · 143 citations
  5. Dense Passage Retrieval for Open-Domain Question AnsweringVladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis et al.EMNLP 2020 · 142 citations

Related papers

  1. Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual EvidenceMohsen Fayyaz, Ali Modarressi, Hinrich Schütze, Nanyun PengACL 2025
  2. Mitigating Bias in RAG: Controlling the EmbedderTaeyoun Kim, Jacob Mitchell Springer, Aditi Raghunathan, Maarten SapACL Findings 2025 · 5 citations
  3. Improving Zero-shot LLM Re-Ranker with Risk MinimizationXiaowei Yuan, Zhao Yang, Yequan Wang, Jun Zhao et al.EMNLP 2024 · 3 citations
  4. Understanding the Behaviors of Environment-aware Information RetrievalRuifeng Yuan, Chaohao Yuan, David Dai, Yu Rong et al.ACL 2026
  5. QuDAR: Query-Wise Dual-Perspective Adaptive RetrievalJoeun Kim, Seunghyouk Yoon, Xuan-Bach Le, Youngeun Nam et al.ACL 2026
Dusk over the sea between two cliffs drawn in fine vertical lines