Yongjie Wang王永杰
Ph.D.
Joint NTU-WeBank Research Centre
Nanyang Technological University
Office: N4-B3b-06, 50 Nanyang Ave, Singapore, 639798
Email: yongjie.wangATntu.edu.sg, yongjie002ATe.ntu.edu.sg
|
|
Biography
I am now a research staff at the Joint NTU-WeBank Research Centre at Nanyang Technological University, under the supervision of Dr. Shen Zhiqi. I received my Ph.D. in July 2023 at the College of Computing and Data Science (CCDS, NTU), under the supervision of
Professor Miao Chunyan and Professor Wang Ke. Before that,
I received a Bachelor's degree from the College of Software, Jilin University, and a Master's degree from the Institute of Computing Technology, Chinese Academy of Sciences,
advised by Professor Zhang Yongdong and Associate Professor Gao Ke.
My research interests are centered on (1) developing trustworthy AI by integrating various explanation techniques to enhance model trustworthiness and robustness; (2) applying modern models (e.g., LLMs) to high-stakes applications.
Exploring the philosophy of explainable AI from multiple disciplines, e.g., causality, psychology, and social science.
Investigating effective retrieval augmented generation to mitigate the LLM hallucination.
Leveraging counterfactual explanations into learning paradigm.
Studying and probing modern Large Language Models (LLMs), such as how in-context learning can enhance their capabilities.
Concept-level explanation, i.e., understanding the high-level representation coined in LLMs.
I am open and welcome to collaborate with researchers with similar interests in XAI/LLM. Feel free to drop me an email.
Publications (*: equal contribution)
-
Yongjie Wang*, Xiaoqi Qiu*, Yu Yue, Xu Guo, Zhiwei Zeng, Yuhong Feng, Zhiqi Shen. A Survey on Natural Language Counterfactual Generation. ( Findings of EMNLP 2024 )
-
Xiaoqi Qiu*, Yongjie Wang*, Xu Guo, Zhiwei Zeng, Yue Yu, Yuhong Feng, Chunyan Miao. PairCFR: Enhancing Model Training on Paired Counterfactually Augmented Data through Contrastive Learning. The 62nd Annual Meeting of the Association for Computational Linguistics ( ACL 24 Main )
-
Ruomei Wang, Wei Guo, Yongjie Wang , Xin Zhou, Jonathan Cyril Leung, Shuo Yan, Lizhen Cui. Hybrid Multimodal Fusion for Graph Learning in Disease Prediction. (Elsevier Method 2024)
-
Yongjie Wang, Tong Zhang, Xu Guo, Zhiqi Shen. Gradient based Feature Attribution in Explainable AI: A Technical Review. (Arxiv Preprint 2024)
-
Ruochen Zhao, Shafiq Joty, Yongjie Wang , Tan Wang. Explaining Language Models' Predictions with High-Impact Concepts. Findings of the Association for Computational Linguistics: EACL 2024
-
Yongjie Wang, Hangwei Qian, Yongjie Liu, Wei Guo, Chunyan Miao. Flexible and Robust Counterfactual Explanations with Minimal Satisfiable Perturbations. 32nd ACM International Conference on Information and Knowledge Management (CIKM' 2023)
-
Yongjie Wang. Counterfactual Explanations for Machine Learning Models on Heterogeneous Data. 2023, Nanyang Technological University (PhD Thesis)
-
Yongjie Wang, Ke Wang, Cheng Long, Chunyan Miao. Summarizing User-Item Matrix By Group Utility Maximization. 2023 ACM Transactions on Knowledge Discovery from Data ((TKDD' 2023), Extension work of ICDM'21)
-
Yongjie Wang, Hangwei Qian and Chunyan Miao, DualCF: Efficient Model Extraction Attack from Counterfactual Explanations, ACM Conference on Fairness, Accountability, and Transparency 2022 (FAccT' 2022)
-
Yongjie Wang , Qinxu Ding, Ke Wang, Yue Liu, Xingyu Wu, Jinglong Wang, Yong Liu and Chunyan Miao, The Skyline of Counterfactual Explanations for Machine Learning Decision Models, 30th ACM International Conference on Information and Knowledge Management (CIKM' 2021).
-
Yongjie Wang , Ke Wang, Cheng Long, Chunyan Miao. Summarizing User-Item Matrix By Group Utility Maximization. 2021 IEEE International Conference on Data Mining (ICDM’21)
-
Yong Luo, Huaizheng Zhang, Yongjie Wang , Yonggang Wen, and Xinwen Zhang. ResumeNet: A Learning-based Framework for Automatic Resume Quality Assessment. 2018 IEEE International Conference on Data Mining (ICDM'18)
Experience
-
Webank-NTU Singapore Joint Research Institute, Nanyang Technological University
Oct. 2023 - Present
Research Fellow
Topic: LLM Interpretability, Counterfactual Explanations, In-context Learning, Retrieval Augmented Generation.
-
Alibaba-NTU Singapore Joint Research Institute, Nanyang Technological University
Aug. 2019 - Oct. 2023
Research Associate
Topic: Counterfactual explanation, Feature attribution, Model Security.
-
Advanced Computer Research Center, Institute of Computing Technology, CAS
Jan. 2016 - Jul. 2018
Research Assistant
Topic: Image processing, and retrieval on large-scale systems.
Professional Activities
Conference Reviews: EMNLP (2024), WWW (2025)
Journal Reviews: TNNLS (2024)
Hobbies
Basketball (shooting guard), Badminton (中羽3级), Table Tennis, Tennis, Skiing, Running
© Yongjie Wang | Last updated: Dec 2024