Preprints HeadEdit: Calibrating Language Model Behavior Through the Frozen Unembedding Matrix Zirui He, Haiyan Zhao, Jingyu Hu, Yinghao Wu, Chenxi Yuan, Yingcong Li, Yandong Bai, Mengnan Du Preprint, 2026 Faithful Activation Verbalization: Reducing Hallucinations in LLM Representation Interpretation Haiyan Zhao, Zirui He, Wei Shi, Huiqi Deng, Na Zou, Mengnan Du Preprint, 2026 DynaCF: Mitigating Shortcut Learning in Reward Models via Dynamic Counterfactual Sensitivity Fengyuan Liu, Yongliang Miao, Zirui He, Yanguang Liu, Fei Sun, Mengnan Du Preprint, 2026 LogitTrace: Detecting Benchmark Contamination via Layerwise Logit Trajectories Zirui He, Haiyan Zhao, Yingcong Li, Ali Payani, Mengnan Du Preprint, 2026 RealRoute: Dynamic Query Routing System via Retrieve-then-Verify Paradigm Jiahe Liu, Qinkai Yu, Jingcheng Niu, Xi Zhu, Zirui He, Zhen Xiang, Fan Yang, Jinman Zhao Preprint, 2026
