Explainable and Automatic Interruption Strategies for Full-Duplex Conversational AI

Takyoung Kim, Dilek Hakkani-Tür

Keywords: Conversational AI, Full-duplex Dialogue, Explainable Interruption

TL;DR: We study the criteria of "good interruption," enabling effective and collaborative full-duplex communication.

Presentation Preference: Open to it if recommended by organizers

Abstract:

This research focuses on the development of **explainable and automatic interruption criteria** for conversational AI systems. Current half-duplex dialogue agents often struggle with turn-taking, resulting in interactions that feel unnatural or inefficient. To address this, we propose a framework that enables AI to identify and execute **"good interruptions",** those that are timely, context-aware, and perceived as cooperative rather than disruptive. Crucially, these interruptions are grounded in observable conversational cues, ensuring that the system’s behavior is both interpretable and justifiable.

By formalizing the conditions under which an interruption is appropriate, this work supports large-scale dialogue generation systems with transparent decision-making processes. A key application is in language support scenarios. For instance, when a non-native speaker hesitates while searching for a word, an AI agent equipped with our model could recognize the pause, infer the context, and offer the appropriate term in a way that feels helpful rather than intrusive. Similarly, in educational settings, an AI tutor could provide real-time feedback or clarification without breaking the conversational flow.

Ultimately, this research advances the goal of more natural and trustworthy human-AI interaction by integrating explainability directly into the mechanics of conversational behavior, with particular attention to the nuanced dynamics of interruption. This is expected to reduce an excessive dependency on black-box proprietary language models for generating interruptive behavior.

Submission Number: 10