Explainable AI from Cognitive Science perspectives
Project Description
In this project, students will have hands-on experiences in conducting research on explainable AI from cognitive science perspectives. It will involve alignment, evaluation, and benchmarking of large language models from the perspectives of human cognition and human-AI interaction.
Supervisor
HSIAO, Janet Hui-wen
Quota
2
Course type
UROP1100
Applicant's Roles
The applicant will help the research team implement algorithms for alignment, evaluation, or benchmarking of large language models. Basic knowledge about machine learning and programming skills are required.
Applicant's Learning Objectives
- To learn about the literature on explainable AI from human cognition perspectives.
- To leann about methods for alignment, evaluation, or benchmarking of large language models and have hands-on experience in implementation.
- To leann about methods for alignment, evaluation, or benchmarking of large language models and have hands-on experience in implementation.
Complexity of the project
Challenging