Author

Zhen Yang

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Feb 2026

Patch the Distribution Mismatch: RL Rewriting Agent for Stable Off-Policy SFT

This work forms data rewriting as a policy-learning problem and trains a lightweight LoRA rewriting policy with reinforcement learning that optimizes question-answering-style distributional alignment and semantic diversity under a hard task-consistency gate, producing verified supervision for downstream SFT.

Jia-Cheng Wang, Zhi-Jie Liu, Ping Jian et al. · 0 citations

#artificial intelligence Mar 2026

The Struggle Between Continuation and Refusal: A Mechanistic Analysis of the Continuation-Triggered Jailbreak in LLMs

This work focuses on a continuation-triggered jailbreak phenomenon, whereby simply relocating a continuation-triggered instruction suffix can substantially increase jailbreak success rates and proposes Head Competition Steering (HCS), a mechanistically grounded inference-time strategy that explicitly leverages the comp...

Yong Deng, Zhen Yang, Ping Jian et al. · arXiv.org · 1 citation