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 spurious features (a.k.a. implicit noise). While previous works have explored spurious features in LLMs, they are limited to specific features (e.g., formats) and narrow scenarios (e.g., ICL). In this work, we statistically confirm the presence of spurious features in the RAG paradigm, a robustness problem caused by the sensitivity of LLMs to semantic-agnostic features. Moreover, we provide a comprehensive taxonomy of spurious features and empirically quantify their impact through controlled experiments. Further analysis reveals that not all spurious features are harmful and they can even be beneficial sometimes. Extensive evaluation results across multiple LLMs suggest that spurious features are a widespread and challenging problem in the field of RAG. The code and dataset will be released to facilitate future research. We release all codes and data at: $\\\href{https://github.com/maybenotime/RAG-SpuriousFeatures}{https://github.com/maybenotime/RAG-SpuriousFeatures}$.

翻译：鲁棒性已成为检索增强生成（RAG）系统在现实世界应用中部署的关键属性。现有研究主要关注对显式噪声（例如，文档语义）的鲁棒性，却忽视了伪特征（亦称隐式噪声）。尽管先前工作已探索了大型语言模型（LLM）中的伪特征，但其研究局限于特定特征（例如，格式）和狭窄场景（例如，上下文学习）。在本工作中，我们通过统计方法证实了RAG范式中伪特征的存在，这是一个由LLM对语义无关特征的敏感性所引发的鲁棒性问题。此外，我们提出了一个全面的伪特征分类体系，并通过受控实验实证量化了其影响。进一步分析表明，并非所有伪特征都是有害的，它们有时甚至可能是有益的。在多个LLM上进行的大规模评估结果表明，伪特征是RAG领域中一个普遍存在且具有挑战性的问题。我们将发布代码和数据集以促进未来研究。所有代码和数据发布于：$\\\href{https://github.com/maybenotime/RAG-SpuriousFeatures}{https://github.com/maybenotime/RAG-SpuriousFeatures}$。