CV

Education

• Ph.D. in Management Science and Engineering, Shanghai University of Finance and Economics (SUFE), Sept 2022 – Jul 2026 (expected)
  • School of Computing and Artificial Intelligence (SCAI)
  • Advisor: Prof. Yun Chen
• Visiting Student, Southern University of Science and Technology (SUSTech), Apr 2023 – Apr 2026
  • Advisor: Prof. Guanhua Chen
• M.S. in Computer Software and Theory, Jinan University, Sept 2018 – Jul 2021
• B.S. in Economic Statistics, Dongbei University of Finance and Economics, Sept 2014 – Jul 2018

Research Interests

• LLM Safety & Red-teaming: automated adversarial attack generation, jailbreak detection and defense
• LLM Alignment: scalable oversight, reward modeling, preference learning
• LLM Robustness: out-of-distribution generalization, calibration
• LLM Unlearning: capability-preserving unlearning, robust unlearning against relearning attacks

Publications

Towards Bridging the Reward-Generation Gap in Direct Alignment Algorithms

Modeling LLM Unlearning as an Asymmetric Two-Task Learning Problem

Representation-Guided Parameter-Efficient LLM Unlearning

Automatic Robustness Stress Testing of LLMs as Mathematical Problem Solvers

Enhancing Uncertainty Estimation in LLMs with Expectation of Aggregated Internal Belief

SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters

Distract Large Language Models for Automatic Jailbreak Attack

Pruning Adatperfusion with Lottery Ticket Hypothesis

BERT4GCN: Using BERT Intermediate Layers to Augment GCN for Aspect-based Sentiment Classification

Talks

Teaching