Suhong Moon

Hi! I'm a Machine Learning Researcher at Apple Foundation Model team. I graduated from UC Berkeley with my PhD in December 2025, where I was part of Berkeley Artificial Intelligence Research (BAIR) under the guidance of Prof.John Canny. My research interests include:

Create diverse and consistent virtual personas
Higher order approximations
Understanding the societal impact of LLMs

Email / Scholar / X / LinkedIn / Github

Selected Publications

Deep Binding of Language Model Virtual Personas: a Study on Approximating Political Partisan Misperceptions
Minwoo (Josh) Kang*, Suhong Moon*, Seung Hyeong Lee, Ayush Raj, Joseph Suh, David M. Chan, John Canny
COLM 2025
Paper | Code | Dataset

Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions
Joseph Suh*, Erfan Jahanparast*, Suhong Moon*, Minwoo (Josh) Kang*, Serina Chang
ACL 2025
Paper | Code | Dataset

Rediscovering the Latent Dimensions of Personality with Large Language Models as Trait Descriptors
Joseph Suh*, Suhong Moon*, Minwoo (Josh) Kang*, David M. Chan, John Canny
NeurIPS 2024, Workshop on Behavioral Machine Learning
Paper

Virtual Personas for Language Models via an Anthology of Backstories
Suhong Moon*, Marwa Abdulhai*, Minwoo (Josh) Kang*, Joseph Suh*, Widyadewi Soedarmadji, Eran Kohen Behar, David M. Chan, John Canny
EMNLP 2024
Paper | Code | Dataset | Blog

An LLM Compiler for Parallel Function Calling
Sehoon Kim*, Suhong Moon*, Ryan Tabrizi, Nicholas Lee, Michael W. Mahoney, Kurt Keutzer, Amir Gholami,
ICML 2024
Paper | Code

template