Hello, I'm Shenzhe (Cho) Zhu🤔

I am a researcher with interest in Trustworthy AI, LLM Interpretability & Alignment, Multimodal LLM, and Generative Agents. Currently, I am a third-year Computer Science student at the University of Toronto, supervised by William Cunningham in the SocialAI lab. Additionally, I collaborate remotely with the PRADA Lab at King Abdullah University of Science and Technology(KAUST).

email: cho.zhu at mail.utoronto.ca

CV Scholar Github Linkedin

News

Jun 2024: Excited to share that I start my research intern in PRADA lab of KAUST focusing on LLM Interpretability.
May 2024: Good news, I began working with Prof.William Cunningham, focusing on LLM agents for Social Cognition.
May 2024: I’ve released my first arxiv paper Exploring knowledge graph-based neural-symbolic system from application perspective.
April 2024: I received work-study job offer from Urban Data Research Center in UofT, I will start my NLP analyst position this summer.
Dec 2023: Excited to share that I started my Deep Learning research work under the supervision of Prof.Xujie Si.

Publications/Pre-prints

SC-Bench: Evaluating LLM-based Generative Agents through Social Cognitive Criteria

Shenzhe Zhu*, Eric Xue*, Rebekah Gelpi, William A. Cunningham

In Processing

This paper introduces SC-BENCH, a comprehensive benchmark designed to evaluate abilities and limitations of language models in social cognition.

PDF arXiv

Minagen: A Minimal Testing Ground for Building Cognitive Architectures for Generative Agents

Eric Xue*, Shenzhe Zhu*, Rebekah Gelpi, William A. Cunningham

In Processing

Minagen develops and tests cognitive architectures for generative AI agents, offering a minimalistic platform for researchers to explore and test cognitive modeling and AI ideas.

PDF arXiv

Exploring knowledge graph-based neural-symbolic system from application perspective

Shenzhe Zhu, Shengxiang Sun

arXiv, 2024

This survey paper explores KG-based neural-symbolic integration, enhancing neural reasoning, improving symbolic accuracy, and combining both

PDF arXiv

Projects

Career Navigator: LLM & Knowledge Graph-Based Job Recommender Engine

Shenzhe Zhu

Career Navigator is an job recommendation service based on LLM and Knowledge Graph, It addresses challenges students face on the CSM platform, improving job search efficiency.

Code

Experience

Texas A&M University
Research Assistant, advised by Prof. ZhengZhong Tu
July 2024 - Current
PRADA LAB - King Abdullah University of Science and Technology
Collaborative Researcher
June 2024 - Current
Social AI Lab - University of Toronto
Research Assistant, advised by Prof. William Cunningham
May 2024 - Current
CoNSens Lab - University of Toronto
Research Assistant, advised by Prof. Matthias Niemeier
May 2024 - Aug 2024
Urban Data Research Center - University of Toronto
NLP Analyst
May 2024 - Aug 2024
University of Toronto Scarborough
Data Analyst Intern
Jan 2024 - May 2024

Education

University of Toronto
B.S. in Computer Science.
Fall 2022 - Current