Author

XiuYu Zhang

View on Semantic Scholar

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.

Preprint Aug 2026

LMSM: LLM Security Framework Inspired by Linux Security Modules

This work presents Language Model Security Modules (LMSM), a security framework that adapts the separation behind Linux Security Modules (LSM) to LLM serving and gives advances in interpretability and model-internal analysis a common path to runtime enforcement.

XiuYu Zhang, Bo-Nan Ruan, Junfeng Fang et al. · 0 citations

#natural language process... Jun 2026

Self-Evaluation Is Already There: Eliciting Latent Judge Calibration in Base LLMs with Minimal Data

Self-Evaluation Elicitation (SEE) is introduced, a method that surfaces a latent ability to predict how a judge will score its own output through a short cycle comprising a calibration-coupled reinforcement learning phase that improves the answer and predicts the judge, followed by a masked distillation phase that sharpens the prediction while leaving the answer untouched.

XiuYu Zhang, Yingyu Shan, Junfeng Fang et al. · arXiv.org · 2 citations