Large Pre-Trained Language Models have demonstrated state-of-the-art performance in
different downstream tasks, including dialogue state tracking and end-to-end response …

Generating faithful and fast responses is crucial in the knowledge-grounded dialogue.
Retrieval Augmented Generation (RAG) strategies are effective but are inference inefficient …

Recent studies have demonstrated significant improvements in selection tasks, and a
considerable portion of this success is attributed to incorporating informative negative …

Task-oriented dialogue systems that employ external knowledge to generate informative
responses have become an important field of research. This paper outlines our contribution …