Publications
My research focuses on improving the reliability and safety of large language models, with applications in AIGC detection and model alignment.
CoCoNUTS: Concentrating on Content while Neglecting Uninformative Textual Styles for AI-Generated Peer Review Detection
ACL 2026 Main Conference • 2026 • Accepted
CoCoNUTS is a content-focused framework and dataset for AI-generated peer review detection. Its CoCoDet detector reduces reliance on superficial writing styles while improving accuracy and robustness.