@inproceedings{yang-etal-2026-quantifying,
    title = "Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Data",
    author = "Yang, Shiping  and
      Wu, Jie  and
      Ding, Wenbiao  and
      Wu, Ning  and
      Liang, Shining  and
      Gong, Ming  and
      Li, Hongzhi  and
      Zhang, Hengyuan  and
      Chang, Angel X  and
      Zhang, Dongmei",
    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.1545/",
    pages = "33479--33499",
    ISBN = "979-8-89176-390-6",
    abstract = "Robustness has become a critical attribute for the deployment of RAG systems in real-world applications. Existing research focuses on robustness to explicit noise (e.g., document semantics) but overlooks implicit noise (spurious features). Moreover, previous studies on spurious features in LLMs are limited to specific types (e.g., formats) and narrow scenarios (e.g., ICL). In this work, we identify and study spurious features in the RAG paradigm, a robustness issue caused by the sensitivity of LLMs to semantic-agnostic features. We then propose a novel framework,\textit{SURE}, to empirically quantify the robustness of RALMs against spurious features. Beyond providing a comprehensive taxonomy and metrics for evaluation, the framework{'}s data synthesis pipeline facilitates training-based strategies to improve robustness. Further analysis suggests that spurious features are a widespread and challenging problem in the field of RAG. Our code is available at https://anonymous.4open.science/r/RAG-SpuriousFeatures-62B3."
}