A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems

This survey provides a comprehensive review of research on multi-turn dialogue systems, with a particular focus on multi-turn dialogue systems based on large language models (LLMs). This paper aims to (a) give a summary of existing LLMs and approaches for adapting LLMs to downstream tasks; (b) elaborate recent advances in multi-turn dialogue systems, covering both LLM-based open-domain dialogue (ODD) and task-oriented dialogue (TOD) systems, along with datasets and evaluation metrics; (c) discuss some future emphasis and recent research problems arising from the development of LLMs and the increasing demands on multi-turn dialogue systems.

Introduction. Multi-turn dialogue systems that can generate natural and meaningful responses to communicate with humans are a Multi-turn dialogue systems can be divided into TOD systems and ODD systems. TOD systems assist users in Conventional dialogue systems primarily rely on rule-based approaches and retrieval-based methods. Rule-based enhanced by the emergence of pre-trained LLMs.

Discussion / Conclusion. 10 CONCLUSION evaluation metrics derived from the outputs of multi-turn dialogue systems, which aid in assessing and understanding