Zhiting Mei
Papers
2
Total Citations
29
H-Index
2
About
Zhiting Mei is a rising researcher at the forefront of trustworthy artificial intelligence, with a primary focus on uncertainty quantification for large language models (LLMs). Her work addresses a critical challenge in modern AI: ensuring that powerful generative models are not only capable but also reliable and transparent. Mei’s most cited paper, a comprehensive survey on uncertainty quantification for LLMs, has already garnered 26 citations since its 2025 publication, establishing her as a key voice in this emerging field. In this work, she systematically taxonomizes existing methods for measuring model confidence, identifies open research challenges such as calibration and epistemic uncertainty, and charts a roadmap for future directions. By tackling the propensity of LLMs to produce plausible but incorrect outputs, Mei’s contributions directly support safer deployment of AI in high-stakes domains like healthcare, law, and content generation. Her research bridges the gap between theoretical rigor and practical trustworthiness, making her work essential reading for students and engineers seeking to build more accountable AI systems. As the demand for reliable LLMs grows, Zhiting Mei’s insights will continue to shape the next generation of robust and transparent language technologies.
Research Focus
Key Achievements
Top Papers
- 1
- 2