Recent advances in neural approaches greatly improve task-oriented dialogue (TOD)
systems which assist users to accomplish their goals. However, such systems rely on costly …

Recently, there have merged a class of task-oriented dialogue (TOD) datasets collected
through Wizard-of-Oz simulated games. However, the Wizard-of-Oz data are in fact …

Recently, increasing research interests have focused on retrieval augmented generation
(RAG) to mitigate hallucination for large language models (LLMs). Following this trend, we …

Most existing task-oriented dialog (TOD) systems track dialog states in terms of slots and
values and use them to query a database to get relevant knowledge to generate responses …

Retrieval augmented generation (RAG) has emerged as a paradigm to address problems
like hallucination in dialog systems based on large language model (LLM). Retrieval model …

Task-oriented dialog (TOD) aims to assist users in achieving specific goals through multi-
turn conversation. Recently, good results have been obtained based on large pre-trained …

Dialogue modeling problems severely limit the real-world deployment of neural
conversational models and building a human-like dialogue agent is an extremely …

With the widespread popularisation of intelligent technology, task-based dialogue systems
(TOD) are increasingly being applied to a wide variety of practical scenarios. As the key …