@inproceedings{zeng-etal-2025-towards,
    title = "Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective",
    author = "Zeng, Shenglai  and
      Zhang, Jiankun  and
      Li, Bingheng  and
      Lin, Yuping  and
      Zheng, Tianqi  and
      Everaert, Dante  and
      Lu, Hanqing  and
      Liu, Hui  and
      Liu, Hui  and
      Xing, Yue  and
      Cheng, Monica Xiao  and
      Tang, Jiliang",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.naacl-long.151/",
    pages = "2952--2969",
    ISBN = "979-8-89176-189-6",
    abstract = "Retrieval-Augmented Generation (RAG) systems have shown promise in enhancing the performance of Large Language Models (LLMs). However, these systems face challenges in effectively integrating external knowledge with the LLM{'}s internal knowledge, often leading to issues with misleading or unhelpful information. This work aims to provide a systematic study on knowledge checking in RAG systems. We conduct a comprehensive analysis of LLM representation behaviors and demonstrate the significance of using representations in knowledge checking. Motivated by the findings, we further develop representation-based classifiers for knowledge filtering. We show substantial improvements in RAG performance, even when dealing with noisy knowledge databases. Our study provides new insights into leveraging LLM representations for enhancing the reliability and effectiveness of RAG systems."
}