Publications

* denotes equal contributions

2026

  1. multi-agent-safety.png
    Divide-and-Conquer Attacks on LLM Agents: Orchestrating Multi-Step Jailbreaks in Tool-Enabled Systems
    Xiaofeng Lin*, Yukai Yang*, Daniel Guo, Sahil Arun Nale, Charles Fleming, and Guang Cheng
    2026
  2. uq-llm.png
    A Systematic Assessment of Weak-to-Strong Confidence Prediction in Large Language Models
    Yukai Yang*, Tracy Zhu*, Marco Morucci, and Tim G. J. Rudner
    Transactions on Machine Learning Research, 2026

2024

  1. uq-llm.png
    Weak-to-Strong Confidence Prediction
    Yukai Yang*, Tracy Zhu*, Marco Morucci, and Tim G. J. Rudner
    In NeurIPS 2024 Workshop on Statistical Foundations of LLMs, 2024