Jingyu Hu

Jingyu Hu

PhD Student in Engineering Mathematics

Jingyu Hu

I’m currently a second-year PhD candidate in Engineering Mathematics at University of Bristol funded by EPSRC-DTP. I received my MSc in Data Science and my BSc in Computer Science and Technology. My research interests are broadly in the ethics and trustworthiness (e.g., explainability, fairness) of AI (LLMs, graphs). The resume can be found here.

Data migration is in progress, including contents merging from the previous webpage, and different GitHub accounts: @fairxai (project-based), @ym21669 (current, teaching-based), @jingcs (blue-sky, some non-tech notes).

Publications

LLM LLMs | Fairness Fairness/Alignment | XAI Explainability/Interpretability

  • Hu, J., Yang, M., Du, M. ,& Liu, W., (2025). Fine-Grained Interpretation of Political Opinions in Large Language Models. arXiv preprint. Preprint | LLM XAI

  • Shu D, Zhao H, Hu J., Liu W., Cheng L. & Du, M. (2025) Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability[J]. arXiv preprint. Preprint | LLM Fairness XAI

  • Hu, J., Bo, H., Hong, J., Liu, X., & Liu, W. (2025). Mitigating Degree Bias Adaptively with Hard-to-Learn Nodes in Graph Contrastive Learning. Under-review. Fairness
  • Hu, J., Liu, W., & Du, M. (2024). Strategic Demonstration Selection for Improved Fairness in LLM In-Context Learning. EMNLP 2024. Paper | Code | Demo | LLM Fairness
  • Yang, R., Hu, J., Li, Z., Mu, J., Yu, T., Xia, J., … & Xiong, H. (2024). Interpretable machine learning for weather and climate prediction: A review. Atmospheric Environment, 120797. Paper | XAI
  • Hu, J., Hong, J., Du, M., & Liu, W. (2024). ProxiMix: Enhancing Fairness with Proximity Samples in Subgroups. AEQUITAS ECAI 2024. Paper | Fairness
  • Hu, J., Liang, Y., Zhao, W., McAreavey, K., and Liu, W. (2023) An Interactive XAI Interface with Application in Healthcare for Non-experts. xAI 2023. Paper | Demo | XAI
  • Li, M., Hu, J., and Ho Ryu K. An Efficient Tool for Semantic Biomedical Document Analysis SIST 2021. Demo
  • Hu J., Li M,, Zhang Z., et al. An Efficient Semantic Document Similarity Calculation Method Based on Double-Relations in Gene Ontology. FITAT.

Projects

You may find the details of these projects here.

  • Neural Networks with Bayesian Inference in ICU Data Slides
  • Single-cell Differential Analysis with Explainable Machine Learning Models Slides
  • Real-time Shanghai Yangshan Port’s AIS analyze .Net system Code
  • National Natural Science Foundation of China Project (No. 61702324) Large-scale text mining, ontology-based graph.
  • Self-testing and analyzing software based on Windows and Android platforms

Skills

  • Language: (Native) Chinese; (Familiar, PTE:72) English; (Familiar, JLPT: N2) Japanese
  • Programming/Scripting: Python, Java, C#, SQL, C++, Matlab; Pytorch, PEFT
  • Tech: AWS, VPS, SpringBoot, HTML, Elastic Search, Android Studio, Git, Neo4j, Mysql, Flask
  • Reviewer: ACL, ECAI, AISTATS, AAAI ReLM, Journal of Pattern Recognition, ACM Computing Surveys

visitor tracker