Yinzhou Wang

Yinzhou Wang

Student

Biography

Hi! I recently graduated from Dartmouth College. While at University of Washington, I was a Mary Gates Research Scholar. My interest lies at the intersection of NLP, HCI, Informatics and Mental health. These are the research topics deeply interest me: 1) LLM-enabled pychotherapy 2) Cultural alignment in LLMs 3) Efficient synthetic dialogue generation 4) Automatic evaluation for health dialogue systems. 5) AI-assited mental health invertentions.

Interests
  • LLM-enabled Psychotherapy
  • Huamn-Language Model Interaction
  • Cultural Adaptation
Education

  • MS in Quantitative Biomedical Sciences, 2023

    Dartmouth College

  • BA in Math, 2022

    University of Washington

Publications

Yinzhou Wang, Serena Jinchen Xie, Amandalynne Paullada, Diana Louden, Magaly Ramirez, Trevor Cohen, Weichao Yuwen (2023). Can Natural Language Processing Support Cultural Adaptation of Internet- and Mobile-based Health Interventions? A Scoping Review. Journal of Biomedical Informatics (Under Review).

William R Kearns, Jessica Bertram, Myra Divina, Lauren Kemp, Yinzhou Wang, Alex Marin, Trevor Cohen, Weichao Yuwen (2023). Bridging the Skills Gap: Evaluating an AI-Assisted Provider Platform to Support Care Providers with Empathetic Delivery of Protocolized Therapy. AMIA Annu Symp Proc. 2023 (Accepted).

Project

A Virtual Cognitive Behavioral Therapist- From Fine-tuning to Deployment
This project aims to develop an LLM-enabled CBT therapist to expand CBT’s accessibility. A large portion of this report describes the process of training, evaluating, and deploying LLMs for CBT. Results show that these LLMs generally follow CBT principles but there is a large room for improvement. The effectiveness of these LLMs is unclear and thus a clinical trial is in preparation. In the end, limitations, implications, and future work are discussed. The conclusion of this report states that expert involvement is critical and it might be worth considering to re-design toward the concept of human-LLM collaboration.
A Virtual Cognitive Behavioral Therapist- From Fine-tuning to Deployment

Recent Posts

Building a Conversational AI with Memory on AWS Series - Fine-tune (QLoRA) Llama-2-7b-chat with Dialogue Data and Deploy in Sagemaker
Training Llama-2-7b-chat model on Dialogue data with QLoRA, merge the adapter with the model correctly, and deploy the merged model on Sagemaker
Dec 9, 2023 0 min read
Building a Conversational AI with Memory on AWS Series - Fine-tune (QLoRA) Llama-2-7b-chat with Dialogue Data and Deploy in Sagemaker
Building a Conversational AI with Memory on AWS Series - Fine-tune (QLoRA) Falcon-7b with Dialogue Data and Deploy in Sagemaker
Training falcon-7b model on Dialogue data with QLoRA, merge the adapter with the model correctly, and deploy the merged model on Sagemaker
Nov 30, 2023 0 min read
Building a Conversational AI with Memory on AWS Series - Fine-tune (QLoRA) Falcon-7b with Dialogue Data and Deploy in Sagemaker
Building a Conversational AI with Memory on AWS Series - Prepare Your Dialogue Data for Fine-tuning Falcon and Llama2-chat on SageMaker
Format your dialogue data for self-supervising training falcon-7b model and instruction-tuning the llama2-7b-chat model.
Nov 28, 2023 0 min read
Building a Conversational AI with Memory on AWS Series - Prepare Your Dialogue Data for Fine-tuning Falcon and Llama2-chat on SageMaker
Building a Conversational AI with Memory on AWS Series - AWS Overview
A overview of the backend architecture and AWS services for a conversational AI with memmory.
Nov 26, 2023 0 min read
Building a Conversational AI with Memory on AWS Series - AWS Overview