Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.15347 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913038696710144 |
|---|---|
| author | Tang, Albert |
| author_facet | Tang, Albert |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_15347 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SocialWise: LLM-Agentic Conversation Therapy for Individuals with Autism Spectrum Disorder to Enhance Communication Skills Tang, Albert Human-Computer Interaction Artificial Intelligence Information Retrieval Multiagent Systems H.5.2; I.2; J.3; J.4 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. |
| title | SocialWise: LLM-Agentic Conversation Therapy for Individuals with Autism Spectrum Disorder to Enhance Communication Skills |
| topic | Human-Computer Interaction Artificial Intelligence Information Retrieval Multiagent Systems H.5.2; I.2; J.3; J.4 |
| url | https://arxiv.org/abs/2604.15347 |