Moxuan Zheng

Independent Researcher

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Constitutional AI & AI Ethics (1)Reasoning & Chain-of-Thought (1)Red-Teaming & Adversarial Robustness (1)

Frequent co-authors

Lixing Lin (1)Juli You (1)Yue Li (1)Luyun Lin (1)

Papers (1)

May 24, 2026

May 24, 2026·also Adelaide University, Citigroup, Columbia, Independent Researcher +1

Reflect-Guard: Enhancing LLM Safeguards against Adversarial Prompts via Logical Self-Reflection

LLM safety classifiers can be made dramatically more robust against jailbreaks by teaching them to "think twice" via lightweight, self-reflection fine-tuning.

Lixing Lin, Juli You, Yue Li +4

Constitutional AI & AI Ethics Reasoning & Chain-of-Thought Red-Teaming & Adversarial Robustness

Search

Moxuan Zheng

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)