Shreedhar Jangam | University of California, Santa Cruz

About Me

Shreedhar Jangam is an undergraduate student advised by Prof. Leilani Gilpin in the Department of Computer Science and Engineering at UC Santa Cruz. His current research at the AEIA Lab focuses on the applications of generative and explainable systems, such as Large Language Models and their trustworthiness in various domains. Outside of research, Shreedhar enjoys backpacking, and practicing his wilderness EMT skills.

Research Interests

XAI (Explainable AI): Understanding how AI works, learning to make AI more transparent, and making sure AI can be trusted.
LLMs (Large Language Models): Studying model architectures. Ensuring that the model’s responses are explainable.
Reinforcement Learning: Exploring new approaches to RL. Currently learning applications and interpretability methods for Decision Transformers.
Autonomous Vehicles: Currently on hold.

Publications

arXiv

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

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

arXiv preprint 2310.11207, 2023

PDF BibTex Preprint

News

[Oct. 2023] I submitted my first paper!
[Feb. 2024] I gave a presentation on the transformer architecture Link.
[Apr. 2024] I’m starting a research internship at Embry–Riddle Aeronautical University this summer.
[May. 2024] Our paper got the UCSC Deans’ Undergraduate Research Award Link

Interests and Activities

Community Engagement

UCSC Emergency Medical Services Club [Link]
Certified NOLS Wilderness First Responder (WFR) [Link]
Eagle Scout: Troop 92 [Link]