Dream to Chat: Model-based Reinforcement Learning on Dialogues with User Belief Modeling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Yue, Wang, Xiaoyu, Wang, Dan, Jiang, Zhonglin, Gu, Qingqing, Chen, Teng, Xi, Ningyuan, Qu, Jinxian, Chen, Yong, Ji, Luo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918148592107520
author Zhao, Yue
Wang, Xiaoyu
Wang, Dan
Jiang, Zhonglin
Gu, Qingqing
Chen, Teng
Xi, Ningyuan
Qu, Jinxian
Chen, Yong
Ji, Luo
author_facet Zhao, Yue
Wang, Xiaoyu
Wang, Dan
Jiang, Zhonglin
Gu, Qingqing
Chen, Teng
Xi, Ningyuan
Qu, Jinxian
Chen, Yong
Ji, Luo
contents World models have been widely utilized in robotics, gaming, and auto-driving. However, their applications on natural language tasks are relatively limited. In this paper, we construct the dialogue world model, which could predict the user's emotion, sentiment, and intention, and future utterances. By defining a POMDP, we argue emotion, sentiment and intention can be modeled as the user belief and solved by maximizing the information bottleneck. By this user belief modeling, we apply the model-based reinforcement learning framework to the dialogue system, and propose a framework called DreamCUB. Experiments show that the pretrained dialogue world model can achieve state-of-the-art performances on emotion classification and sentiment identification, while dialogue quality is also enhanced by joint training of the policy, critic and dialogue world model. Further analysis shows that this manner holds a reasonable exploration-exploitation balance and also transfers well to out-of-domain scenarios such as empathetic dialogues.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16876
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dream to Chat: Model-based Reinforcement Learning on Dialogues with User Belief Modeling
Zhao, Yue
Wang, Xiaoyu
Wang, Dan
Jiang, Zhonglin
Gu, Qingqing
Chen, Teng
Xi, Ningyuan
Qu, Jinxian
Chen, Yong
Ji, Luo
Computation and Language
Artificial Intelligence
World models have been widely utilized in robotics, gaming, and auto-driving. However, their applications on natural language tasks are relatively limited. In this paper, we construct the dialogue world model, which could predict the user's emotion, sentiment, and intention, and future utterances. By defining a POMDP, we argue emotion, sentiment and intention can be modeled as the user belief and solved by maximizing the information bottleneck. By this user belief modeling, we apply the model-based reinforcement learning framework to the dialogue system, and propose a framework called DreamCUB. Experiments show that the pretrained dialogue world model can achieve state-of-the-art performances on emotion classification and sentiment identification, while dialogue quality is also enhanced by joint training of the policy, critic and dialogue world model. Further analysis shows that this manner holds a reasonable exploration-exploitation balance and also transfers well to out-of-domain scenarios such as empathetic dialogues.
title Dream to Chat: Model-based Reinforcement Learning on Dialogues with User Belief Modeling
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2508.16876