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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yi, Zihao, Ouyang, Jiarui, Xu, Zhe, Liu, Yuwen, Liao, Tianhao, Luo, Haohao, Shen, Ying
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911105846083584
author Yi, Zihao
Ouyang, Jiarui
Xu, Zhe
Liu, Yuwen
Liao, Tianhao
Luo, Haohao
Shen, Ying
author_facet Yi, Zihao
Ouyang, Jiarui
Xu, Zhe
Liu, Yuwen
Liao, Tianhao
Luo, Haohao
Shen, Ying
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_18013
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems
Yi, Zihao
Ouyang, Jiarui
Xu, Zhe
Liu, Yuwen
Liao, Tianhao
Luo, Haohao
Shen, Ying
Computation and Language
Artificial Intelligence
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.
title A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2402.18013