@inproceedings{sato-etal-2025-proactive,
    title = "Proactive User Information Acquisition via Chats on User-Favored Topics",
    author = "Sato, Shiki  and
      Baba, Jun  and
      Hentona, Asahi  and
      Iwata, Shinji  and
      Yoshimoto, Akifumi  and
      Yoshino, Koichiro",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.131/",
    doi = "10.18653/v1/2025.findings-emnlp.131",
    pages = "2418--2443",
    ISBN = "979-8-89176-335-7",
    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"
}