@inproceedings{wang-etal-2025-adaptive,
    title = "Adaptive Retrieval-Augmented Generation for Conversational Systems",
    author = "Wang, Xi  and
      Sen, Procheta  and
      Li, Ruizhe  and
      Yilmaz, Emine",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.findings-naacl.30/",
    pages = "491--503",
    ISBN = "979-8-89176-195-7",
    abstract = "With the success of integrating large language models into the development of conversational systems, many studies have shown the effectiveness of retrieving and augmenting external knowledge for informative responses. While many existing studies agree on the necessity of Retrieval Augmented Generation (RAG), further investigation into the necessity and value of applying RAG to every turn of the conversation is needed. In this study, we propose to investigate the need for each turn of system response to be augmented with external knowledge. In particular, by leveraging human judgements on the binary choice of adaptive augmentation, we develop RAGate, a gating model, which models conversation context and relevant inputs to predict if a conversational system requires RAG for improved responses. We conduct extensive experiments on devising and applying RAGate to conversational models, joined with well-rounded analyses of various conversational scenarios. Our experimental results and analysis indicate the effective application of RAGate in RAG-based conversational systems in identifying if system responses require RAG to generate high-quality responses with high confidence. This study also identifies and shows the correlation between the generation{'}s confidence level and the relevance of the augmented knowledge. We have also released the implementation code and resources in https://github.com/wangxieric/RAGate."
}