A Comparative Study on Language Models for Task-Oriented Dialogue Systems

Abstract: The recent development of LLMs has shown promising results by achieving state-of-the-art performance on various natural language tasks by fine-tuning pretrained models. In task-oriented dialogue (ToD) systems, LLMs can be used for end-to-end training without relying on dialogue state tracking to track the dialogue history but allowing the LLMs to generate responses according to the context given as input. This paper conducts a comparative study to show the effectiveness and strength of using recent pretrained models for fine-tuning, such as BART and T5, on endto-end ToD systems. The experimental results show substantial performance improvements after LLM fine-tuning. The models produce more fluent responses after adding knowledge to the context that guides the model to avoid hallucination and generate accurate entities in the generated responses. Furthermore, we found that BART and T5 outperform GPT-based models in BLEU and F1 scores and achieve state-of-the-art performance in a ToD system.