2 papers
cs.AI2026
Mitigating Reasoning-Induced Misalignment via Safety-Direction Penalty
Yipeng Zhao, Qishun Yang, Shenzhe Zhu +2
Reasoning-Induced Misalignment, where fine-tuning on reasoning data containing no harmful content, including mathematics, code, and problem-solving with chain-of-thought traces can…
cs.AI2026
AISPA: User-Centric System Prompt Auditing for Large Language Model Applications
Xiangning Lin, Shenzhe Zhu, Shu Yang +23
System prompts are instructions configured by developers to govern the behaviors of foundation models in AI applications. They are used throughout commercial AI products, but are r…