|
Hi, my name is Guangyao Dou (ηͺ¦ε θ). I'm an incoming Computer Science PhD student at the Center for Language and Speech Processing at Johns Hopkins University, where I will be advised by Prof. Benjamin Van Durme. I am also a second-year Data Science master's student at the University of Pennsylvania. I conduct NLP research under the guidance of Prof. Chris Callison-Burch and Prof. Eric Wong. I also collaborate closely with Prof. Kaize Ding at Northwestern University. Previously, I earned a B.S. in Computer Science from Brandeis University, where I graduated with honors as a member of Phi Beta Kappa (top 10%). My research interests lie in GenAI Safety, AI Privacy, and Trustworthy AI. Email / Master's Thesis / Google Scholar / X (Twitter) / Github / LinkedIn |
|
|
|
|
| 2025 |
|
Guangyao Dou, Zheyuan Liu, Qing Lyu, Kaize Ding, Eric Wong Proceedings of NAACL 2025 (Findings). We propose Stable Sequential Unlearning (SSU), a novel framework designed to unlearn copyrighted content from LLMs over multiple time steps. Our approach works by identifying and removing specific weight updates in the model's parameters that correspond to copyrighted content. We improve unlearning efficacy by introducing random labeling loss and ensuring the model retains its general-purpose knowledge by adjusting targeted parameters. |
|
Zheyuan Liu, Guangyao Dou, Mengzhao Jia, Zhaoxuan Tan, Qingkai Zeng, Yongle Yuan, Meng Jiang Proceedings of NAACL 2025 (Main). We introduce Multimodal Large Language Model Unlearning Benchmark (MLLMU-Bench), a novel benchmark aimed at advancing the understanding of multimodal machine unlearning. MLLMU-Bench consists of 500 fictitious profiles and 153 profiles for public celebrities, each profile feature over 14 customized question-answer pairs, evaluated from both multimodal (image+text) and unimodal (text) perspectives. |
| 2024 |
|
Zheyuan Liu, Guangyao Dou, Zhaoxuan Tan, Yijun Tian, Meng Jiang Proceedings of ACL (Findings), 2024. We introduce Selective Knowledge negation Unlearning (SKU), a novel unlearning framework for LLMs, designed to eliminate harmful knowledge while preserving utility on normal prompts. |
|
Zheyuan Liu*, Guangyao Dou*, Yijun Tian, Chunhui Zhang, Eli Chien, Ziwei Zhu Proceedings of The Web Conference (WWW), 2024. We present Controllable Machine Unlearning (ConMU), a novel framework designed to facilitate the calibration of MU. |
|
|
 |
Amazon Payment Service
Seattle, WA, USA 2021.05 - 2021.08 Software Development Engineer Intern |
|
|
 |
University of Pennsylvania
Philadelphia, PA, USA 2023.08 - present MSE in Data Science GPA: 4.00 / 4.00 |
 |
Brandeis University
Waltham, MA, USA 2019.08 - 2023.05 B.S. in Computer Science GPA: 3.98 / 4.00 |
|
|
|