Promoting Real-Time Reflection in Synchronous Communication with Generative AI

TL;DR

The paper tackles real-time reflection in synchronous communication, a challenging task due to cognitive load and limited immediate feedback. It conducts a targeted literature review of recent systems across remote meetings, lectures, and practice talks, classifies interaction patterns and design decisions, and analyzes how Generative AI can shift these patterns. Key contributions include a taxonomy of reflection-support patterns, three interaction paradigms (user-initiated, proactive, continuous display), and actionable design implications for integrating Generative AI, including interpretability, proactiveness, and persona grounding. The findings offer practical guidance for building usable, proactive reflective tools that augment speaker awareness and performance in educational and professional settings.

Abstract

Real-time reflection plays a vital role in synchronous communication. It enables users to adjust their communication strategies dynamically, thereby improving the effectiveness of their communication. Generative AI holds significant potential to enhance real-time reflection due to its ability to comprehensively understand the current context and generate personalized and nuanced content. However, it is challenging to design the way of interaction and information presentation to support the real-time workflow rather than disrupt it. In this position paper, we present a review of existing research on systems designed for reflection in different synchronous communication scenarios. Based on that, we discuss design implications on how to design human-AI interaction to support reflection in real time.