Exploring Explainability and Interpretability in Generative AI
Abstract
This presentation explores methods and challenges in making generative AI systems more explainable and interpretable, focusing on techniques to understand model behavior and decision-making processes.
Date
Sep 15, 2024
Location
Kyoto University, Kyoto, Japan
Kyoto,
Presentation at YRRSDS 2024 and SIGDIAL 2024 at Kyoto University, Kyoto, Japan.
Author: Shiyuan, Huang
Shiyuan Huang
Ph.D. Student
I am a Ph.D. student in the Department of Computer Science and Engineering at UC Santa Cruz, under the supervision of Dr. Leilani Gilpin and Dr. Ian Lane. My research primarily revolves around the explainability of NLP models.