@inproceedings{li-etal-2026-align,
    title = "Align Documents to Questions: Question-Oriented Document Rewriting for Retrieval-Augmented Generation",
    author = "Li, Jiaang  and
      Mao, Zhendong  and
      Wang, Quan  and
      Wan, Yuning  and
      Zhang, Yongdong",
    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.884/",
    pages = "17838--17849",
    ISBN = "979-8-89176-395-1",
    abstract = "Retrieval-Augmented Generation (RAG) enhances the factuality of Large Language Models (LLMs) by incorporating retrieved documents and/or generated context. However, LLMs often exhibit a stylistic bias when presented with mixed contexts, favoring fluent but hallucinated generated content over factually grounded yet disorganized retrieved evidence. This phenomenon reveals that the utility of retrieved information is bottlenecked by its presentation. To bridge this gap, we propose \textbf{QREAM}, a style-controlled rewriter that aligns retrieved documents with a question-oriented style while preserving facts, better for LLM readers to utilize. Our framework consists of two stages: (1) \textbf{QREAM-ICL}, which uses stylistic seeds to guide iterative rewriting exploration; and (2) \textbf{QREAM-FT}, a lightweight student model distilled from denoised ICL outputs. QREAM-FT employs dual-criteria rejection sampling, filtering based on answer correctness and factual consistency to ensure high-quality supervision. QREAM seamlessly integrates into existing RAG pipelines as a plug-and-play module. Experiments demonstrate that QREAM consistently enhances advanced RAG pipelines, yielding up to 8{\%} relative improvement with negligible latency overhead, effectively balancing question relevance with factual grounding."
}