@inproceedings{kim-etal-2025-text,
    title = "Text Overlap: An {LLM} with Human-like Conversational Behaviors",
    author = "Kim, JiWoo  and
      Chang, Minsuk  and
      Bak, JinYeong",
    editor = "Hale, James  and
      Deuksin Kwon, Brian  and
      Dutt, Ritam",
    booktitle = "Proceedings of the Third Workshop on Social Influence in Conversations (SICon 2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.sicon-1.10/",
    pages = "124--136",
    ISBN = "979-8-89176-266-4",
    abstract = "Traditional text-based human-AI interactions typically follow a strict turn-taking approach. This rigid structure limits conversational flow, unlike natural human conversations, which can freely incorporate overlapping speech. However, our pilot study suggests that even in text-based interfaces, overlapping behaviors such as backchanneling and proactive responses lead to more natural and functional exchanges. Motivated by these findings, we introduce text-based overlapping interactions as a new challenge in human-AI communication, characterized by real-time typing, diverse response types, and interruptions. To enable AI systems to handle such interactions, we define three core tasks: deciding when to overlap, selecting the response type, and generating utterances. We construct a synthetic dataset for these tasks and train OverlapBot, an LLM-driven chatbot designed to engage in text-based overlapping interactions. Quantitative and qualitative evaluations show that OverlapBot increases turn exchanges compared to traditional turn-taking systems, with users making 72{\%} more turns and the chatbot 130{\%} more turns, which is perceived as efficient by end-users. This finding supports overlapping interactions and enhances communicative efficiency and engagement."
}