@inproceedings{goyal-etal-2026-masking,
    title = "Masking or Mitigating? Deconstructing the Impact of Query Rewriting on Retriever Biases in {RAG}",
    author = "Goyal, Agam  and
      Mukherjee, Koyel  and
      Saxena, Apoorv  and
      Phukan, Anirudh  and
      Chandrasekharan, Eshwar  and
      Sundaram, Hari",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.414/",
    pages = "8517--8530",
    ISBN = "979-8-89176-395-1",
    abstract = "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 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."
}