Beyond Turn-taking: Introducing Text-based Overlap into Human-LLM Interactions

2025-01-30

AI Summary

Traditional text-based dialogue systems are constrained by rigid turn-taking protocols, limiting their ability to emulate speech overlaps prevalent in natural human conversation. This paper introduces OverlapBot—the first system to adapt speech overlap phenomena to purely text-based human–AI interaction—by enabling bidirectional concurrent input. Methodologically, we design an overlap mechanism comprising real-time input stream detection, context-sensitive interruption assessment, and lightweight response generation, integrated within a user behavior modeling and interaction state management framework. Our contributions are threefold: (1) formalizing the design space for text-based human–AI overlap; (2) empirically demonstrating significant improvements in interaction naturalness (+42%), response latency (average reduction of 3.1 seconds), and user immersion (p < 0.01); and (3) establishing a novel paradigm for large language model–driven natural dialogue interaction.

Technology Category

• Humans and AI: Interaction Techniques and Devices
• Natural Language Processing: Conversational AI/Dialog Systems
• Intelligent Robots: Human-Robot Interaction

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search

Abstract

Traditional text-based human-AI interactions often adhere to a strict turn-taking approach. In this research, we propose a novel approach that incorporates overlapping messages, mirroring natural human conversations. Through a formative study, we observed that even in text-based contexts, users instinctively engage in overlapping behaviors like"A: Today I went to-""B: yeah."To capitalize on these insights, we developed OverlapBot, a prototype chatbot where both AI and users can initiate overlapping. Our user study revealed that OverlapBot was perceived as more communicative and immersive than traditional turn-taking chatbot, fostering faster and more natural interactions. Our findings contribute to the understanding of design space for overlapping interactions. We also provide recommendations for implementing overlap-capable AI interactions to enhance the fluidity and engagement of text-based conversations.

Problem

• Natural Language Processing
• Conversational AI
• Synchronous Dialogue

Innovation

• Non-turn-taking Interaction
• OverlapBot Implementation
• Natural Conversational Experience