FaciliTrain: Practicing Facilitation Skills through AI-Simulated Group Dialogue
2026-07-12 • Human-Computer Interaction
Human-Computer Interaction
AI summaryⓘ
The authors created FaciliTrain, a voice-based system that helps people practice leading small group conversations using AI participants and feedback. They studied 24 participants, finding that both trained and untrained groups performed similarly in a live test. However, those who used FaciliTrain felt less comfortable afterward, while the others felt more comfortable. The authors identified key insights about how people learn facilitation skills with AI and how voice interactions affect practice. They suggest ways to improve voice-based AI training for social skills.
facilitationinclusive dialogueAI simulationvoice-based trainingiterative feedbackmixed-methods studythematic analysisinterpersonal skillsself-reflectionpilot study
Authors
Hang Jiang, Yuanxin Zhu, Diyi Yang, Yoon Kim, Deb Roy, Jad Kabbara
Abstract
Skilled facilitation supports inclusive small-group dialogue, but deliberate practice is hard to scale: it depends on expert coaches, live practice partners, and iterative feedback. We present FaciliTrain, a voice-based training system in which learners step into the facilitator role of an AI-simulated multi-participant conversation, apply five evidence-based techniques, and receive structured AI feedback to support reflection. We report findings from a mixed-methods study with 24 participants, conducted as a formative study (N = 12) and a controlled pilot (N = 12; 6 treatment, 6 control). Both conditions achieved comparable accuracy on a live evaluation task, though treatment participants' self-rated comfort declined significantly while control participants' comfort improved (p = .018). Reflexive thematic analysis identifies four themes: the taxonomy externalizes implicit facilitation intuitions; Making Connections is the most cognitively demanding technique; voice acts as a deliberate-response forcing function; and participants overwhelmingly preferred AI feedback over self-practice. We discuss design implications for voice-based, AI-supported interpersonal skill training at scale.