@inproceedings{xu-etal-2026-rag,
    title = "{RAG} in the Wild: On the (In)effectiveness of {LLM}s with Mixture-of-Knowledge Retrieval Augmentation",
    author = "Xu, Ran  and
      Zhuang, Yuchen  and
      Yu, Yue  and
      Wang, Haoyu  and
      Shi, Wenqi  and
      Yang, Carl",
    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.849/",
    pages = "17191--17206",
    ISBN = "979-8-89176-395-1",
    abstract = "Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge retrieved at inference time. While RAG demonstrates strong performance on benchmarks largely derived from general-domain corpora like Wikipedia, its effectiveness under realistic, diverse retrieval scenarios remains underexplored. We evaluate RAG systems using MassiveDS, a large-scale datastore with mixture of knowledge, and identified critical limitations: retrieval mainly benefits smaller models, rerankers add minimal value, and no single retrieval source consistently excels. Moreover, current LLMs struggle to route queries across heterogeneous knowledge sources. These findings highlight the need for adaptive retrieval strategies before deploying RAG in real-world settings."
}