Proactive User Information Acquisition via Chats on User-Favored Topics
Preprint
Abstract
Chat-oriented dialogue systems designed to provide tangible benefits, such as sharing the latest news or preventing frailty in senior citizens, often require Proactive acquisition of specific user Information via chats on user-faVOred Topics (PIVOT). This study proposes the PIVOT task, designed to advance the technical foundation for these systems. In this task, a system needs to acquire the answers of a user to predefined questions without making the user feel abrupt while engaging in a chat on a predefined topic. We found that even recent large language models (LLMs) show a low success rate in the PIVOT task. We constructed a dataset suitable for the analysis to develop more effective systems. Finally, we developed a simple but effective system for this task by incorporating insights obtained through the analysis of this dataset.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- A Survey on Recent Advances in LLM-Based Multi-turn Dialogue SystemsACM Computing Surveys, 2025
- Integrating Belief-Desire-Intention agents with large language models for reliable human–robot interaction and explainable Artificial IntelligenceEngineering Applications of Artificial Intelligence, 2024
- Modeling a Conversational Agent using BDI Framework2023
- NewsDialogues: Towards Proactive News Grounded Conversation2023
- Empathetic Persuasion: Reinforcing Empathy and Persuasiveness in Dialogue Systems2022
- Spoken Dialogue Robot for Watching Daily Life of Elderly People2021
- End-to-End Trainable Non-Collaborative Dialog SystemProceedings of the AAAI Conference on Artificial Intelligence, 2020
- A Survey on Dialogue SystemsACM SIGKDD Explorations Newsletter, 2017
- Detecting Dementia Through Interactive Computer AvatarsIEEE Journal of Translational Engineering in Health and Medicine, 2017
- Conversational system for information navigation based on POMDP with user focus trackingComputer Speech & Language, 2015