@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
Kwon, Brian Deuksin 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://aclanthology.org/2025.sicon-1.10/",
doi = "10.18653/v1/2025.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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2025-text">
<titleInfo>
<title>Text Overlap: An LLM with Human-like Conversational Behaviors</title>
</titleInfo>
<name type="personal">
<namePart type="given">JiWoo</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minsuk</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">JinYeong</namePart>
<namePart type="family">Bak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Social Influence in Conversations (SICon 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Hale</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="given">Deuksin</namePart>
<namePart type="family">Kwon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritam</namePart>
<namePart type="family">Dutt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-266-4</identifier>
</relatedItem>
<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.</abstract>
<identifier type="citekey">kim-etal-2025-text</identifier>
<identifier type="doi">10.18653/v1/2025.sicon-1.10</identifier>
<location>
<url>https://aclanthology.org/2025.sicon-1.10/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>124</start>
<end>136</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Text Overlap: An LLM with Human-like Conversational Behaviors
%A Kim, JiWoo
%A Chang, Minsuk
%A Bak, JinYeong
%Y Hale, James
%Y Kwon, Brian Deuksin
%Y Dutt, Ritam
%S Proceedings of the Third Workshop on Social Influence in Conversations (SICon 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-266-4
%F kim-etal-2025-text
%X 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.
%R 10.18653/v1/2025.sicon-1.10
%U https://aclanthology.org/2025.sicon-1.10/
%U https://doi.org/10.18653/v1/2025.sicon-1.10
%P 124-136
Markdown (Informal)
[Text Overlap: An LLM with Human-like Conversational Behaviors](https://aclanthology.org/2025.sicon-1.10/) (Kim et al., SICon 2025)
ACL