SocialWise: LLM-Agentic Conversation Therapy for Individuals with Autism Spectrum Disorder to Enhance Communication Skills
For individuals with ASD who lack access to expensive role-play therapy, SocialWise offers a scalable, browser-based alternative, though the work is incremental as it applies existing LLM and RAG techniques to a new domain.
SocialWise uses LLM agents with a therapeutic RAG knowledge base to provide on-demand conversation practice and feedback for individuals with ASD, addressing the lack of scalable, low-cost communication therapy. The prototype demonstrates feasibility but reports no concrete performance numbers.
Autism Spectrum Disorder (ASD) affects more than 75 million people worldwide. However, scalable support for practicing everyday conversation is scarce: Low-cost activities such as story reading yield limited improvement. At the same time, effective role-play therapy demands expensive, in-person sessions with specialists. SocialWise bridges this gap through a browser-based application that pairs LLM conversational agents with a therapeutic retrieval augmented generation (RAG) knowledge base. Users select a scenario (e.g., ordering food, joining a group), interact by text or voice, and receive instant, structured feedback on tone, engagement, and alternative phrasing. The SocialWise prototype, implemented with Streamlit, LangChain, and ChromaDB, runs on any computer with internet access, and demonstrates how recent advances in LLM can provide evidence-based, on-demand communication coaching for individuals with ASD.