About

Sketched portrait of Baixiang Huang

Hi there! I’m Baixiang, a CS PhD candidate at Emory University, advised by Dr. Kai Shu. My research focuses on building controllable LLMs and agents across three dimensions: factuality [ICLR'25], safety [AAAI'26] and ethical alignment [AAAI'26], and personalization [arXiv'25], particularly through model editing 🛠️, a technique that enables precise and efficient modifications to large language models while preserving their overall capabilities.

Previously, I have worked on authorship attribution [EMNLP'24, KDD'24], which aims to identify the author of a text based on their unique writing style.

In my free time, I enjoy the outdoors 🏔️🧗‍♂️ and staying active, especially running 🏃‍♂️ and weightlifting. I also find joy in cooking 🥘, baking 🍰, and playing 🎹 🎸.

Publications

Preprints

Tools and Resources

Medium Blog