DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Minzheng, Zhang, Xinghua, Chen, Kun, Xu, Nan, Yu, Haiyang, Huang, Fei, Mao, Wenji, Li, Yongbin
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912403013238784
author Wang, Minzheng
Zhang, Xinghua
Chen, Kun
Xu, Nan
Yu, Haiyang
Huang, Fei
Mao, Wenji
Li, Yongbin
author_facet Wang, Minzheng
Zhang, Xinghua
Chen, Kun
Xu, Nan
Yu, Haiyang
Huang, Fei
Mao, Wenji
Li, Yongbin
contents Large language models (LLMs) enabled dialogue systems have become one of the central modes in human-machine interaction, which bring about vast amounts of conversation logs and increasing demand for dialogue generation. The dialogue's life-cycle spans from $\textit{Prelude}$ through $\textit{Interlocution}$ to $\textit{Epilogue}$, encompassing rich dialogue elements. Despite large volumes of dialogue-related studies, there is a lack of systematic investigation into the dialogue stages to frame benchmark construction that covers comprehensive dialogue elements. This hinders the precise modeling, generation and assessment of LLMs-based dialogue systems. To bridge this gap, in this paper, we introduce a new research task--$\textbf{D}$ialogue $\textbf{E}$lement $\textbf{MO}$deling, including $\textit{Element Awareness}$ and $\textit{Dialogue Agent Interaction}$, and propose a novel benchmark, $\textbf{DEMO}$, designed for a comprehensive dialogue modeling and assessment. On this basis, we further build the DEMO agent with the adept ability to model dialogue elements via imitation learning. Extensive experiments on DEMO indicate that current representative LLMs still have considerable potential for enhancement, and our DEMO agent performs well in both dialogue element modeling and out-of-domain tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2412_04905
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling
Wang, Minzheng
Zhang, Xinghua
Chen, Kun
Xu, Nan
Yu, Haiyang
Huang, Fei
Mao, Wenji
Li, Yongbin
Computation and Language
Artificial Intelligence
Machine Learning
Large language models (LLMs) enabled dialogue systems have become one of the central modes in human-machine interaction, which bring about vast amounts of conversation logs and increasing demand for dialogue generation. The dialogue's life-cycle spans from $\textit{Prelude}$ through $\textit{Interlocution}$ to $\textit{Epilogue}$, encompassing rich dialogue elements. Despite large volumes of dialogue-related studies, there is a lack of systematic investigation into the dialogue stages to frame benchmark construction that covers comprehensive dialogue elements. This hinders the precise modeling, generation and assessment of LLMs-based dialogue systems. To bridge this gap, in this paper, we introduce a new research task--$\textbf{D}$ialogue $\textbf{E}$lement $\textbf{MO}$deling, including $\textit{Element Awareness}$ and $\textit{Dialogue Agent Interaction}$, and propose a novel benchmark, $\textbf{DEMO}$, designed for a comprehensive dialogue modeling and assessment. On this basis, we further build the DEMO agent with the adept ability to model dialogue elements via imitation learning. Extensive experiments on DEMO indicate that current representative LLMs still have considerable potential for enhancement, and our DEMO agent performs well in both dialogue element modeling and out-of-domain tasks.
title DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2412.04905