Zhe Yu

Bio. I am a Research Assistant at the Hong Kong University of Science and Technology (Guangzhou), advised by Prof. Chengwei Qin. I am also a Research Intern at the Binjiang Institute of Zhejiang University (IFRC Lab), working on trustworthy language models with Dr. Meng Han and Dr. Wenpeng Xing. I am pursuing a B.Eng. in Artificial Intelligence at the Communication University of Zhejiang.

Research. From latent knowledge to reliable action, memory, and verifiable trust. I study how models internally represent knowledge, evidence provenance, conflict, and risk; why those signals fail to guide generation, tool use, and memory; and how monitoring, system safeguards, and verification can make AI systems more reliable.

Research Agenda

Trustworthy agents must not only represent provenance, conflict, and risk internally. These signals should reliably inform what agents say, do, remember, reuse, and learn, while the resulting models and artifacts remain externally verifiable.

01

Internal representation

Understand how models encode knowledge, retrieved evidence, source provenance, conflict, and hallucination risk through white-box monitoring and hidden-state analysis.

02

Action and memory

Study why decodable safety signals fail to guide generation, tool use, and memory updates, and turn monitoring into reliable system safeguards.

03

Verifiable trust

Build accountable deployment mechanisms through information-flow control, model fingerprinting, blockchain, and privacy-preserving verification.

Current themes

  • Multi-agent memory consistency: write validity, contamination, persistence, propagation, and repair.
  • Poisoning defense and credit: separating the source, amplifier, executor, and best remediation target.
  • Runtime monitoring of agent skills: identifying risky skills before unsafe tool actions.

My longer-term goal is to understand environment–verifier–memory co-evolution in lifelong agents: how tasks, evaluation, memory, and oversight should adapt together as agents act, learn, and update over time.

Publications

* Equal contribution. Review statuses are a snapshot dated August 2, 2026.

PLAIT parent-preserving response, claim, and span audit planning framework

PLAIT: From Hallucination Scores to Parent-Preserving Audit Plans

Zhe Yu, Yunzhao Wei, Wenpeng Xing, Wenjie Luo, Zaobo He, Quan Chen, Meng Han

Under review at AAAI 2027

PLAIT converts hallucination scores into parent-preserving response–claim–span audit plans, using whole-plan learning and exact budgeted optimization to capture more unsupported content per review minute.

PDF

Experience & Education

Hong Kong University of Science and Technology (Guangzhou)

Research Assistant, advised by Prof. Chengwei Qin.

Binjiang Institute of Zhejiang University · IFRC Lab

Research Intern, supervised by Dr. Meng Han and Dr. Wenpeng Xing.

University of Malaya

Visiting Student, Kuala Lumpur, Malaysia.

Westlake University

Visiting Student, supervised by Dr. Ziyang Zhang.

Communication University of Zhejiang

B.Eng. in Artificial Intelligence, supervised by Dr. Hao Zeng.

Patents

  1. Zhe Yu, Wenpeng Xing, Meng Han. A hallucination detection method based on dual-path internal state forcing logic for retrieval-augmented generation in large language models. Application No. 202610260408X. Under review.
  2. Meng Han, Zhe Yu, Jiayan Hu, Rongchang Li, Wenpeng Xing, Jingyi Yu, Zhen Hong, et al. A post-processing method, system, device, and medium for hallucination detection in large language models based on adaptive order statistics aggregation. Application No. 2026107898102, filed June 3, 2026. Pending.
  3. Zhe Yu, Jiayan Hu, Jingyi Yu, Weihang Yu, Wenpeng Xing, Jing Xiong, Yourong Chen, Zhen Hong, et al. A hallucination detection method, system, and device for large language models based on multi-dimensional heterogeneous feature fusion. Application No. 2026107899270, filed June 3, 2026. Pending.