Y. Leng

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Constitutional AI & AI Ethics (1)Eval Frameworks & Benchmarks (1)Red-Teaming & Adversarial Robustness (1)

Frequent co-authors

Junjie Chu (1)Y. Qu (1)Yiting Qu (1)Ye Leng (1)

Papers (1)

Mar 12, 2026

4d ago·also Flexera, TU Delft

Understanding LLM Behavior When Encountering User-Supplied Harmful Content in Harmless Tasks

Even the most advanced LLMs like GPT-5.2 and Gemini-3-Pro often fail to recognize and refuse to process harmful content embedded within seemingly harmless tasks.

Junjie Chu, Y. Qu, Yiting Qu +6

Constitutional AI & AI Ethics Eval Frameworks & Benchmarks Red-Teaming & Adversarial Robustness

Search

Y. Leng

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)