I received my Ph.D. from the University of Science and Technology of China (USTC) in November 2025. My research interests include shortcut learning, robustness and generalization, post-training, reward hacking, and legal intelligence.

In December 2025, I joined the LongCat-Interaction team, where I work on post-training, agentic reinforcement learning, and self-evolving agents. We are actively recruiting — feel free to reach out if you are interested in joining us!

Email / Google Scholar / GitHub

Publications

  1. 2026

    STRIDE: Strategic Iterative Decision-Making for Retrieval-Augmented Multi-Hop Question Answering

    Wei Chen, Lili Zhao, Zhi Zheng, Huijun Hou, Tong Xu. SIGIR, 2026.

  2. 2025

    Beneath the Surface: Exposing and Mitigating Surface Learning in Large Language Models

    Lili Zhao, Yang Wang, Wei Chen, Yu Yuan, Qi Liu, Dongjie Guo, Kai Han, Shijin Wang. Preprint, 2025.

  3. 2025

    MiMu: Mitigating Multiple Shortcut Learning Behavior of Transformers

    Lili Zhao, Qi Liu, Wei Chen, Liyi Chen, Ruijun Sun, Min Hou, Yang Wang, Shijin Wang, Pingping Ren, Jiafeng Zhou. Frontiers of Computer Science, 2025.

  4. 2025

    Evaluating Large Language Models through Role-Guide and Self-Reflection: A Comparative Study

    Lili Zhao, Yang Wang, Qi Liu, Mengyun Wang, Wei Chen, Zhichao Sheng, Shijin Wang. ICLR, 2025.

  5. 2025

    Simulating Human-like Learning Dynamics with LLM-Empowered Agents

    Yu Yuan, Lili Zhao, Wei Chen, Guangting Zheng, Kai Zhang, Mengdi Zhang, Qi Liu. arXiv, 2025.

  6. 2025

    Following Occam's Razor: Dynamic Combination of Structured Knowledge for Multi-Hop Question Answering using LLMs

    Wei Chen, Zhi Zheng, Lili Zhao, Huijun Hou, Tong Xu. EMNLP, 2025.

  7. 2024

    Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models

    Yu Yuan, Lili Zhao, Kai Zhang, Guangting Zheng, Qi Liu. EMNLP, 2024.

  8. 2024

    CoMi: Correct and Mitigate Shortcut Learning Behavior in Deep Neural Networks

    Lili Zhao, Qi Liu, Linan Yue, Wei Chen, Liyi Chen, Ruijun Sun, Chao Song. SIGIR, 2024.

  9. 2024

    Event Grounded Criminal Court View Generation with Cooperative (Large) Language Models

    Linan Yue, Qi Liu, Lili Zhao, Li Wang, Weibo Gao, Yanqing An. SIGIR, 2024.

  10. 2024

    Double-Checker: Large Language Model as a Checker for Few-Shot Named Entity Recognition

    Wei Chen, Lili Zhao, Zhi Zheng, Tong Xu, Yang Wang, Enhong Chen. EMNLP, 2024.

  11. 2023

    HeProto: A Hierarchical Enhancing ProtoNet Based on Multi-Task Learning for Few-Shot Named Entity Recognition

    Wei Chen, Lili Zhao, Pengfei Luo, Tong Xu, Yi Zheng, Enhong Chen. CIKM, 2023.

  12. 2023

    Diagnosis then Aggregation: An Adaptive Ensemble Strategy for Keyphrase Extraction

    Xin Jin, Qi Liu, Linan Yue, Ye Liu, Lili Zhao, Weibo Gao, Zheng Gong, Kai Zhang, Haoyang Bi. CICAI, 2023. 🏆 Finalist of Best Paper Award (Top-3)

  13. 2022

    CPEE: Civil Case Judgment Prediction Centering on the Trial Mode of Essential Elements

    Lili Zhao, Linan Yue, Yanqing An, Yuren Zhang, Jun Yu, Qi Liu, Enhong Chen. CIKM, 2022.

  14. 2021

    Legal Judgment Prediction with Multiple Perspectives on Civil Cases

    Lili Zhao, Linan Yue, Yanqing An, Ye Liu, Kai Zhang, Weidong He, Yanmin Chen, Senchao Yuan, Qi Liu. CICAI, 2021.

* Equal contribution. Full list on Google Scholar.