GenAI for Social Work Field Education: Client Simulation with Real-Time Feedback

TL;DR

This paper introduces SWITCH, an AI-powered chatbot that simulates realistic social work client interactions with real-time feedback, enhancing training efficiency and consistency in social work education.

Contribution

The paper presents a novel client simulation system integrating dynamic profiles, skill classification, and MI progression, with improved accuracy through BERT and in-context learning.

Findings

BERT-based classifier outperforms baseline in skill detection

In-context learning with retrieval improves classification accuracy

SWITCH provides scalable, low-cost social work training simulation

Abstract

Field education is the signature pedagogy of social work, yet providing timely and objective feedback during training is constrained by the availability of instructors and counseling clients. In this paper, we present SWITCH, the Social Work Interactive Training Chatbot. SWITCH integrates realistic client simulation, real-time counseling skill classification, and a Motivational Interviewing (MI) progression system into the training workflow. To model a client, SWITCH uses a cognitively grounded profile comprising static fields (e.g., background, beliefs) and dynamic fields (e.g., emotions, automatic thoughts, openness), allowing the agent's behavior to evolve throughout a session realistically. The skill classification module identifies the counseling skills from the user utterances, and feeds the result to the MI controller that regulates the MI stage transitions. To enhance classification accuracy, we study in-context learning with retrieval over annotated transcripts, and a fine-tuned BERT multi-label classifier. In the experiments, we demonstrated that both BERT-based approach and in-context learning outperforms the baseline with big margin. SWITCH thereby offers a scalable, low-cost, and consistent training workflow that complements field education, and allows supervisors to focus on higher-level mentorship.