About me

This is the webpage for Zongjie’s academic research. I’m a final year Ph.D. student at the HKUST, advised by Prof. Shuai Wang.
Currently, I’m visiting the Advanced Software Technologies (AST) Lab at ETH Zurich (ETH), advised by Prof. Zhendong Su.

News

• [2025-04] Our paper Causality-Aided Evaluation and Explanation of Large Language Model-based Code Generation is now accepted by ISSTA 2025
• [2025-04] Our paper DecLLM: LLM-Augmented Recompilable Decompilation for Enabling Programmatic Use of Decompiled Code is now accepted by ISSTA 2025
• [2025-03] Our paper Reeq: Testing and Mitigating Ethically Inconsistent Suggestions of Large Language Models with Reflective Equilibrium is now accepted by TOSEM
• [2025-02] Our paper API-guided Dataset Synthesis to Finetune Large Code Models is now accepted by OOPSLA 2025
• [2025-01] Our paper Low-Cost and Comprehensive Non-textual Input Fuzzing with LLM-Synthesized Input Generators is now accepted by USENIX Security 2025
• [2025-01] Our paper SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner is now accepted by USENIX Security 2025
• [2024-10] Glad to be invited as a PC member at Conference on AI Foundation Models and Software Engineering (FORGE 2025) in ICSE 2025.
• [2024-09] Our paper Split and Merge: Aligning Position Biases in LLM-based Evaluators is now accepted by EMNLP 2024 Main Track
• [2024-08] Our proposal towards Robustness & Fairness in LLM is now accepted by OpenAI.

Long Vision

Ensuring traceable safety on the path towards AGI