Weipeng Jiang (降伟鹏)
About me
I am a fourth-year Ph.D. student at the School of Cyber Science and Engineering, Xi'an Jiaotong University, advised by Prof. Chao Shen. I am also very fortunate to collaborate closely with Prof. Shiqing Ma and Prof. Juan Zhai from Umass Amherst.
Currently, I am a visiting Ph.D. student at Singapore Management University(SMU), under the supervision of Prof. Xiaofei Xie.
My research interests encompass Intersection of Software Engineering and AI (AI4SE, SE4AI) and Trustworthy AI. Specifically, I am actively involved in the following topics:
Effective and Efficient Red Teaming and Auditing for LLM Safety, Fairness, and Privacy;
Evaluation and Application of CodeLLM in Various Software Engineering Tasks;
Software Quality Assurance and Security Analysis for DL (particularly LLM) Infrastructure;
News
[Feb 2025] Fortunate to serve on the Program Committee for The 1st International Workshop on Large Language Model Supply Chain Analysis (LLMSC 2025).
[Jan 2025] Our paper about LLM Jailbreaking is accepted by NAACL Findings 2025.
[Dec 2024] Be invited to serve as a reviewer for ICML 2025.
[Aug 2024] Be invited to serve as a reviewer for ICLR 2025.
[Aug 2024] Be invited to serve as a program committee of Artifact Evaluation Track for ICSE 2025.
[June 2024] New preprint is online From Effectiveness to Efficiency: Comparative Evaluation of Code Generated by LCGMs for Bilingual Programming Questions.
[May 2024] Be invited to serve as a reviewer for NeurIPS 2024.
[Feb 2024] Our paper about Embedding-Service Testing is accepted by FSE'24.
Research Publications
( * indicates equal contribution.)Preprints
-
Holistic Audit Dataset Generation for LLM Unlearning via Knowledge Graph Traversal and Redundancy Removal
Weipeng Jiang, Juan Zhai, Shiqing Ma, Ziyan Lei, Xiaofei Xie, Yige Wang, Chao Shen Arxiv. -
Unveiling Provider Bias in Large Language Models for Code Generation
Xiaoyu Zhang, Juan Zhai, Shiqing Ma, Qingshuang Bao, Weipeng Jiang, Chao Shen, Yang Liu
Arxiv. -
From Effectiveness to Efficiency: Comparative Evaluation of Code Generated by LCGMs for Bilingual Programming Questions
Weipeng Jiang, Xuanqi Gao, Juan Zhai, Shiqing Ma, Xiaoyu Zhang, Chao Shen
Arxiv.
Paper-
An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer
Weipeng Jiang, Zhenting Wang, Juan Zhai, Shiqing Ma, Zhengyu Zhao, Chao Shen
Findings of American Chapter of the Association for Computational Linguistics Findings (NAACL Findings'25) -
STAFF: Speculative Coreset Selection for Task-Specific Fine-tuning
Xiaoyu Zhang, Juan Zhai, Shiqing Ma, Chao Shen, Tianlin Li, Weipeng Jiang, Yang Liu
The 13rd International Conference on Learning Representations (ICLR' 25) (CCF A) -
Efficient DNN-Powered Software with Fair Sparse Models
Xuanqi Gao, Weipeng Jiang, Juan Zhai, Shiqing Ma, Xiaoyu Zhang, Chao Shen
The 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA' 24) (CCF A) -
COSTELLO: Contrastive Testing for Embedding-based Large Language Model as a Service Embeddings
Weipeng Jiang, Juan Zhai, Shiqing Ma, Xiaoyu Zhang, Chao Shen
ACM International Conference on the Foundations of Software Engineering (FSE' 24) (CCF A) -
Black-Box Fairness Testing with Shadow Models
Weipeng Jiang, Chao Shen, Chenhao Lin, Jingyi Wang, Jun Sun, Xuanqi Gao
The 23rd International Conference on Information and Communications Security (ICICS' 23) (CCF C)
Code-
Deep Learning Library Testing: Definition, Methods and Challenges
Xiaoyu Zhang, Weipeng Jiang, Chao Shen, Qi Li, Qian Wang, Chenhao Lin, Xiaohong Guan
ACM Computing Surveys, 2025.(CUSR)(CCF A, IF = 23.8) -
Fairness in Machine Learning: Definition, Testing, Debugging and Application
Xuanqi Gao, Chao Shen, Weipeng Jiang, Chenhao Lin, Qian Li, Qian Wang, Qi Li, Xiaohong Guan
Science China Information Sciences, Volume 67, article number 191201, 2024 (SCIS) (CCF A, IF = 7.3)