@inproceedings{kim-etal-2026-qudar,
    title = "{Q}u{DAR}: Query-Wise Dual-Perspective Adaptive Retrieval",
    author = "Kim, Joeun  and
      Yoon, Seunghyouk  and
      Le, Xuan-Bach  and
      Nam, Youngeun  and
      Kim, Doyoung  and
      Song, Hwanjun  and
      Lee, Jae-Gil",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1791/",
    pages = "38662--38679",
    ISBN = "979-8-89176-390-6",
    abstract = "Retrieval-augmented generation(RAG) systems depend on retrieval modules to supply grounding evidence for large language models. While hybrid approaches combining sparse and dense retrievers improve performance, most rely on fixed weights that ignore query-specific and corpus-specific variation. Similarly, query expansion has long been used to enrich recall, but its integration with original queries is usually static and can introduce noise. We present QuDAR, a dual-perspective adaptive retrieval framework that adapts along two perspectives: retriever type (sparse vs. dense) and query format (original vs.expanded). Leveraging margin-derived confidence (e.g., top-1{--}top-2 score gaps) and blind LLM-based relevance scoring, QuDAR dynamically assigns query-specific weights, fusing lexical specificity with semantic breadth while mitigating noise. QuDAR is lightweight, retriever-agnostic, and broadly applicable. Experiments show consistent gains over static baselines, improving overall retrieval quality and yielding more stable performance across queries."
}