2 papers
cs.CL2026
Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating
Sicheng Wang, Xiangyang Zhu, Han Wang +6
Prior work has shown that fine-tuning large language models on malicious or incorrect outputs in narrow domains can induce broad misalignment and harmful behavior, a phenomenon kno…
cs.CL2026
Automated Safety Benchmarking: A Multi-agent Pipeline for LVLMs
Xiangyang Zhu, Yuan Tian, Zicheng Zhang +6
Large vision-language models (LVLMs) exhibit remarkable capabilities in cross-modal tasks but face significant safety challenges, which undermine their reliability in real-world ap…