Primary supervisor

KokSheik Wong

Co-supervisors

As the number of mental health patients increases, the demand for qualified counselors is on the rise. However, training/practice sessions with actual patients are often limited, let alone meeting a sufficient number of patients of different personalities. This project aims to use large language models to simulate therapy sessions under certain predefined circumstances. This project is co-supervised by a collaborator from the Psychology department in Jeffrey Cheah School of Medicine and Health Sciences.

Student cohort

Double Semester

Aim/outline

This project aims to leverage the capabilities of large language models (LLM) in playing different personas in simulated therapy sessions. The responses generated by different LLM will be analyzed, and the feasibility of using LLM in training psychology (specifically counseling) students will be investigated. If successful, this project will significantly increase the diversity of personalities that trainee counselors meet, and simulated therapy sessions can be conducted as often as needed to sharpen trainee counselors' skills. 

URLs/references

We will be using the freely available LLM models to complete this project. 

Required knowledge

  • Good command in English
  • Prompt engineering
  • Background in psychology / counseling will be great plus.