Explore LLM-enabled Tools to Facilitate Imaginal Exposure Exercises for Social Anxiety

2026-03-26

AI Summary

This study addresses the challenge that individuals with social anxiety often struggle to independently develop effective imaginal exposure scripts, thereby limiting access to this evidence-based intervention. To overcome this barrier, the authors introduce a large language model (LLM) into structured imaginal exposure therapy for the first time, integrating cognitive behavioral therapy principles to co-design, with mental health experts, a tool called ImaginalExpoBot. This system generates vivid, personalized, and clinically appropriate exposure scripts in real time. Findings from a user study (N=19) and therapist evaluations (N=5) demonstrate that the tool effectively supports patients in preparing for anxiety-provoking scenarios, enhancing intervention adaptability while maintaining the therapeutic “window of tolerance.” The results also highlight opportunities for improvement in script continuity and deeper personalization.

Abstract

Social anxiety (SA) is a prevalent mental health challenge that significantly impacts daily social interactions. Imaginal Exposure (IE), a Cognitive Behavioral Therapy (CBT) technique involving imagined anxiety-provoking scenarios, is effective but underutilized, in part because traditional IE homework requires clients to construct and sustain clinically relevant fear narratives. In this work, we explore the feasibility of an LLM-enabled tool that supports IE by generating vivid, personalized exposure scripts. We first co-designed ImaginalExpoBot with mental health professionals, followed by a formative evaluation with five therapists and a user study involving 19 individuals experiencing SA symptoms. Our findings show that LLM-enabled support can facilitate preparation for anxiety-inducing situations while enabling immediate, user-specific adaptation, with scenarios remaining within a therapeutically beneficial "window of tolerance". Our participants and MHPs also identified limitations in continuity and customization, pointing to the need for deeper adaptivity in future designs. These findings offer preliminary design insights for integrating LLMs into structured therapeutic practices in accessible, scalable ways.

Problem

• Social Anxiety
• Imaginal Exposure
• Cognitive Behavioral Therapy
• Fear Narratives
• Therapeutic Homework

Innovation

• LLM-enabled therapy
• Imaginal Exposure
• personalized exposure scripts
• social anxiety
• AI in mental health