About
Photo by Angeline Swinkels
Jiaxu Zhao
I am a PhD candidate at the Eindhoven University of Technology (TU/e) advised by Mykola Pechenizkiy, Meng Fang and Yulong Pei. My research primarily focuses on fairness and bias in large language models, investigating how these systems handle social biases across different cultures and languages. My broader research interests span across AI safety, causal reasoning, and graph neural networks, with emphasis on developing more equitable and robust AI systems for diverse global communities.
Facts
Years of Experience
Supervised Projects
Collaborative Institutions
News
Publications
FS-GNN: Improving Fairness in Graph Neural Networks via Joint Sparsification
Jiaxu Zhao, Tianjin Huang, Shiwei Liu, Jie Yin, Yulong Pei, Meng Fang, Mykola Pechenizkiy
Neurocomputing 2025
Understanding Large Language Model Vulnerabilities to Social Bias Attacks
Jiaxu Zhao, Meng Fang, Fanghua Ye, Ke Xu, Qin Zhang, Joey Tianyi Zhou, Mykola Pechenizkiy
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025 Oral)
Unmasking Style Sensitivity: A Causal Analysis of Bias Evaluation Instability in Large Language Models
Jiaxu Zhao, Meng Fang, Kun Zhang, Mykola Pechenizkiy
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)
CHAmbi: A New Benchmark on Chinese Ambiguity Challenges for Large Language Models
Qin Zhang, Sihan Cai, Jiaxu Zhao, Mykola Pechenizkiy, Meng Fang
Findings of the Association for Computational Linguistics (EMNLP 2024)
More than Minorities and Majorities: Understanding Multilateral Bias in Language Generation
Jiaxu Zhao, Zijing Shi,Yitong Li, Yulong Pei, Ling Chen, Meng Fang, Mykola Pechenizkiy
Findings of the Association for Computational Linguistics (ACL 2024)
On Adversarial Robustness of Language Models in Transfer Learning
Bohdan Turbal, Anastasiia Mazur, Jiaxu Zhao, Mykola Pechenizkiy
NeurIPS 2024 Socially Responsible Language Modelling Research Workshop (SoLaR)
Synergizing Foundation Models and Federated Learning: A Survey
Shenghui Li, Fanghua Ye, Meng Fang, Jiaxu Zhao, Yun-Hin Chan, Edith C-H Ngai, Thiemo Voigt
arXiv preprint arXiv:2406.12844
REST: Enhancing Group Robustness in DNNs Through Reweighted Sparse Training
Jiaxu Zhao, Lu Yin, Shiwei Liu, Meng Fang, Mykola Pechenizkiy
Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2023)
CHBias: Bias Evaluation and Mitigation of Chinese Conversational Language Models
Jiaxu Zhao, Meng Fang, Zijing Shi, Yitong Li, Ling Chen, Mykola Pechenizkiy
In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023)
Gptbias: A comprehensive framework for evaluating bias in large language models
Jiaxu Zhao, Meng Fang, Shirui Pan, Wenpeng Yin, Mykola Pechenizkiy
arXiv preprint arXiv:2312.06315
You can have better graph neural networks by not training weights at all: Finding untrained gnns tickets
Tianjin Huang, Tianlong Chen, Meng Fang, Vlado Menkovski, Jiaxu Zhao, Lu Yin, Yulong Pei, Decebal Constantin Mocanu, Zhangyang Wang, Mykola Pechenizkiy, Shiwei Liu
The First Learning on Graphs Conference (LoG 2022 Best Paper Award)
Twin-GAN for Neural Machine Translation
Jiaxu Zhao, Li Huang, Ruixuan Sun, Liao Bing, Hong Qu
The 13th International Conference on Agents and Artificial Intelligence (ICAART 2021)
Service
Journal Reviewer
Journal of Artificial Intelligence Research (JAIR), Neurocomputing.
Conference Reviewer
ACL 2023, ICML 2024, ACL ARR 2024, EMNLP 2024, ICLR 2025, KDD 2025, ACL ARR 2025, EWAF 2025 Workshop.
Supervised MSc Students
Luc Geven, Saumya Roy
Resume
Education
PhD in Natural Language Processing
11/2021 - Present
Eindhoven University of Technology, Eindhoven, The Netherlands
Supervisor: Prof. Mykola Pechenizkiy, Prof. Meng Fang and Prof. Yulong Pei
MSc in Computer Technology
09/2018 - 07/2021
University of Electronic Science and Technology of China, Chengdu, China
Title: The Research and Solution of Exposure Bias in Neural Machine Translation
Supervisor: Prof. Xiaobin Wang, Prof. Hong Qu
Professional Experience
Assistant Lecturer
10/2024 - 01/2025
2IIG0 Data Mining and Machine Learning Course
Eindhoven University of Technology, Eindhoven, The Netherlands
Programe Mentor
08/2023 - 11/2024
RESPONSIBLE AI FALL 2023 RESEARCH PROGRAM
New York University, U.S.A & Ukrainian Catholic University, Ukraine
Contact
Location
Eindhoven, The Netherlands
j.zhao@tue.nl