作者位次 #2/10ACL 2026Poster· Natural Language Processing
Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Data
Shiping Yang · Jie Wu · Wenbiao Ding · Ning Wu · Shining Liang · Ming Gong · Hongzhi Li · Hengyuan Zhang · Angel X. Chang · Dongmei Zhang
摘要
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 a...