Proactive User Information Acquisition via Chats on User-Favored Topics

Shiki Sato, Jun Baba, Asahi Hentona, Shinji Iwata, Akifumi Yoshimoto, Koichiro Yoshino


Abstract
Chat-oriented dialogue systems that deliver tangible benefits, such as sharing news or frailty prevention for seniors, require proactive acquisition of specific user information via chats on user-favored topics. This study proposes the Proactive Information Acquisition (PIA) task to support the development of these systems. In this task, a system needs to acquire a user’s answers to predefined questions without making the user feel abrupt while engaging in a chat on a predefined topic. We created and analyzed a dataset of 650 PIA chats, identifying key challenges and effective strategies for recent LLMs. Our system, designed from these insights, surpassed the performance of LLMs prompted solely with task instructions. Finally, we demonstrate that automatic evaluation of this task is reasonably accurate, suggesting its potential as a framework to efficiently develop techniques for systems dealing with complex dialogue goals, extending beyond the scope of PIA alone. Our dataset is available at: https://github.com/CyberAgentAILab/PIA
Anthology ID:
2025.findings-emnlp.131
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2418–2443
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.131/
DOI:
Bibkey:
Cite (ACL):
Shiki Sato, Jun Baba, Asahi Hentona, Shinji Iwata, Akifumi Yoshimoto, and Koichiro Yoshino. 2025. Proactive User Information Acquisition via Chats on User-Favored Topics. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 2418–2443, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Proactive User Information Acquisition via Chats on User-Favored Topics (Sato et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.131.pdf
Checklist:
 2025.findings-emnlp.131.checklist.pdf