Saved in:
Bibliographic Details
Main Authors: Wang, Yufeng, Hu, Jinwu, Huang, Ziteng, Lin, Kunyang, Zhang, Zitian, Chen, Peihao, Hu, Yu, Wang, Qianyue, Yu, Zhuliang, Sun, Bin, Xing, Xiaofen, Zheng, Qingfang, Tan, Mingkui
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.12334
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908369231544320
author Wang, Yufeng
Hu, Jinwu
Huang, Ziteng
Lin, Kunyang
Zhang, Zitian
Chen, Peihao
Hu, Yu
Wang, Qianyue
Yu, Zhuliang
Sun, Bin
Xing, Xiaofen
Zheng, Qingfang
Tan, Mingkui
author_facet Wang, Yufeng
Hu, Jinwu
Huang, Ziteng
Lin, Kunyang
Zhang, Zitian
Chen, Peihao
Hu, Yu
Wang, Qianyue
Yu, Zhuliang
Sun, Bin
Xing, Xiaofen
Zheng, Qingfang
Tan, Mingkui
contents Open-domain dialogue systems aim to generate natural and engaging conversations, providing significant practical value in real applications such as social robotics and personal assistants. The advent of large language models (LLMs) has greatly advanced this field by improving context understanding and conversational fluency. However, existing LLM-based dialogue systems often fall short in proactively understanding the user's chatting preferences and guiding conversations toward user-centered topics. This lack of user-oriented proactivity can lead users to feel unappreciated, reducing their satisfaction and willingness to continue the conversation in human-computer interactions. To address this issue, we propose a User-oriented Proactive Chatbot (UPC) to enhance the user-oriented proactivity. Specifically, we first construct a critic to evaluate this proactivity inspired by the LLM-as-a-judge strategy. Given the scarcity of high-quality training data, we then employ the critic to guide dialogues between the chatbot and user agents, generating a corpus with enhanced user-oriented proactivity. To ensure the diversity of the user backgrounds, we introduce the ISCO-800, a diverse user background dataset for constructing user agents. Moreover, considering the communication difficulty varies among users, we propose an iterative curriculum learning method that trains the chatbot from easy-to-communicate users to more challenging ones, thereby gradually enhancing its performance. Experiments demonstrate that our proposed training method is applicable to different LLMs, improving user-oriented proactivity and attractiveness in open-domain dialogues.
format Preprint
id arxiv_https___arxiv_org_abs_2505_12334
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing User-Oriented Proactivity in Open-Domain Dialogues with Critic Guidance
Wang, Yufeng
Hu, Jinwu
Huang, Ziteng
Lin, Kunyang
Zhang, Zitian
Chen, Peihao
Hu, Yu
Wang, Qianyue
Yu, Zhuliang
Sun, Bin
Xing, Xiaofen
Zheng, Qingfang
Tan, Mingkui
Artificial Intelligence
Open-domain dialogue systems aim to generate natural and engaging conversations, providing significant practical value in real applications such as social robotics and personal assistants. The advent of large language models (LLMs) has greatly advanced this field by improving context understanding and conversational fluency. However, existing LLM-based dialogue systems often fall short in proactively understanding the user's chatting preferences and guiding conversations toward user-centered topics. This lack of user-oriented proactivity can lead users to feel unappreciated, reducing their satisfaction and willingness to continue the conversation in human-computer interactions. To address this issue, we propose a User-oriented Proactive Chatbot (UPC) to enhance the user-oriented proactivity. Specifically, we first construct a critic to evaluate this proactivity inspired by the LLM-as-a-judge strategy. Given the scarcity of high-quality training data, we then employ the critic to guide dialogues between the chatbot and user agents, generating a corpus with enhanced user-oriented proactivity. To ensure the diversity of the user backgrounds, we introduce the ISCO-800, a diverse user background dataset for constructing user agents. Moreover, considering the communication difficulty varies among users, we propose an iterative curriculum learning method that trains the chatbot from easy-to-communicate users to more challenging ones, thereby gradually enhancing its performance. Experiments demonstrate that our proposed training method is applicable to different LLMs, improving user-oriented proactivity and attractiveness in open-domain dialogues.
title Enhancing User-Oriented Proactivity in Open-Domain Dialogues with Critic Guidance
topic Artificial Intelligence
url https://arxiv.org/abs/2505.12334