Published several papers including 'Deep Binding of Language Model Virtual Personas: a Study on Approximating Political Partisan Misperceptions', 'Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions', 'Rediscovering the Latent Dimensions of Personality with Large Language Models as Trait Descriptors', 'Virtual Personas for Language Models via an Anthology of Backstories', and 'An LLM Compiler for Parallel Function Calling'.
Research Experience
Involved in multiple research projects related to large language models, virtual personas, and predicting public opinions.
Education
Pursuing a PhD at UC Berkeley, advised by Prof. John Canny.
Background
PhD student in Berkeley Artificial Intelligence (BAIR) at UC Berkeley under the guidance of Prof. John Canny. Interested in human behavior simulation with LLMs.