Publications: 'When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detection' and other papers on mechanistic interpretability and AI applications. Service: Reviewer for ACL, EMNLP, NLPCC in 2025.
Research Experience
Work Experience: Research Intern at MBZUAI (Supervisor: Dr. Xiuying Chen, Topic: Mechanistic Interpretability of LLMs). Position: Research Intern.
Education
Degree: PhD; Institution: MBZUAI; Advisors: Dr. Xiuying Chen and Prof. Preslav Nakov; Time: Since October 2024; Field: Mechanistic Interpretability.
Background
Research Interests: Mechanistic Interpretability (MI), Reliable Application of AI. Background: Lang Gao is currently a first-year PhD student at MBZUAI, focusing on understanding the mechanisms of foundation models and their application issues in personalized content, with the goal of making them more interpretable, controllable, and trustworthy.
Miscellany
Personal Interests: Passionate about the field of interpretability, eager to learn from new perspectives.