InstructTODS: Large Language Models for End-to-End Task-Oriented Dialogue Systems
This work addresses the challenge of building flexible, zero-shot task-oriented dialogue systems for diverse domains, offering a novel off-the-shelf framework that reduces the need for task-specific data.
The paper tackles the problem of adapting large language models (LLMs) for end-to-end task-oriented dialogue systems (TODS) without fine-tuning, achieving comparable performance to fully fine-tuned systems and outperforming state-of-the-art TODS in human evaluations for helpfulness, informativeness, and humanness.
Large language models (LLMs) have been used for diverse tasks in natural language processing (NLP), yet remain under-explored for task-oriented dialogue systems (TODS), especially for end-to-end TODS. We present InstructTODS, a novel off-the-shelf framework for zero-shot end-to-end task-oriented dialogue systems that can adapt to diverse domains without fine-tuning. By leveraging LLMs, InstructTODS generates a proxy belief state that seamlessly translates user intentions into dynamic queries for efficient interaction with any KB. Our extensive experiments demonstrate that InstructTODS achieves comparable performance to fully fine-tuned TODS in guiding dialogues to successful completion without prior knowledge or task-specific data. Furthermore, a rigorous human evaluation of end-to-end TODS shows that InstructTODS produces dialogue responses that notably outperform both the gold responses and the state-of-the-art TODS in terms of helpfulness, informativeness, and humanness. Moreover, the effectiveness of LLMs in TODS is further supported by our comprehensive evaluations on TODS subtasks: dialogue state tracking, intent classification, and response generation. Code and implementations could be found here https://github.com/WillyHC22/InstructTODS/