Proactive User Information Acquisition via Chats on User-Favored Topics
This addresses the challenge for developers of chat-oriented dialogue systems needing to gather user information smoothly without disruption, though it appears incremental as it builds on existing methods with a new dataset and task.
The study tackled the problem of proactively acquiring specific user information during chats on preferred topics, which is crucial for dialogue systems offering benefits like news sharing or frailty prevention, and found that even recent large language models have low success rates, leading to the development of a simple but effective system.
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.