Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations

Shiyuan Huang, Siddarth Mamidanna, Shreedhar Jangam, Yilun Zhou, Leilani H. Gilpin

Abstract

This research investigates whether large language models can effectively explain their own decision-making processes and outputs, analyzing the quality and reliability of LLM-generated self-explanations.

Date
Oct 10, 2024
Event
BayLearn 2024
Location
Apple, Cupertino, California
Cupertino, CA

Presentation at BayLearn 2024 conference at Apple headquarters in Cupertino, California.

Authors: Shiyuan, Huang, Siddarth Mamidanna, Shreedhar Jangam, Yilun Zhou, Leilani H. Gilpin

Large Language Models Explainability Natural Language Processing
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.