I am currently a first-year PhD student at the National University of Singapore, supervised by Prof. Mengling Feng.
Reviewer for NIPS, IJCAI, ACM TIST, with over 10 papers reviewed.
Research Interests: Trustworthy and Agentic LLM • Multi-modality Intelligence in Healthcare
Looking for a summer 26' internship!! 🙏
Warning
Problem: The current name of your GitHub Pages repository ("zhihuichen.netlify.app").
Solution: Please consider renaming the repository to "
zhihuichen.netlify.app", so that your site can be accessed directly at "http://zhihuichen.netlify.app".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}" in index.html.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "Education
-
National University of SingaporePh.D. in Artificial IntelligenceJan. 2025 - present -
The University of Hong KongM.Sc. in Artificial IntelligenceSep. 2022 - Jul. 2024 -
The Chinese University of Hong Kong, ShenzhenB.Sc. in Statistics, Data Science StreamSep. 2018 - May. 2022
Honors & Awards
-
Full Ph.D. Scholarship, National University of Singapore2025
-
Outstanding College Graduate, CUHK-Shenzhen Diligentia College2022
-
Undergraduate Research Excellence Award, CUHK-Shenzhen2021
News
Selected Publications (view all )
DivScore: Zero-Shot Detection of LLM-Generated Text in Specialized Domains
Zhihui Chen, Kai He, Yucheng Huang, Yunxiao Zhu, Mengling Feng
Conference on Empirical Methods in Natural Language Processing (EMNLP) 2025
Detecting LLM-generated text in specialized and high-stakes domains like medicine and law is crucial for combating misinformation and ensuring authenticity. We propose DivScore, a zero-shot detection framework using normalized entropy-based scoring and domain knowledge distillation to robustly identify LLM-generated text in specialized domains. Experiments show that DivScore consistently outperforms state-of-the-art detectors, with 14.4% higher AUROC and 64.0% higher recall at 0.1% false positive rate threshold.
DivScore: Zero-Shot Detection of LLM-Generated Text in Specialized Domains
Zhihui Chen, Kai He, Yucheng Huang, Yunxiao Zhu, Mengling Feng
Conference on Empirical Methods in Natural Language Processing (EMNLP) 2025
Detecting LLM-generated text in specialized and high-stakes domains like medicine and law is crucial for combating misinformation and ensuring authenticity. We propose DivScore, a zero-shot detection framework using normalized entropy-based scoring and domain knowledge distillation to robustly identify LLM-generated text in specialized domains. Experiments show that DivScore consistently outperforms state-of-the-art detectors, with 14.4% higher AUROC and 64.0% higher recall at 0.1% false positive rate threshold.