Dr Zihao Fu
- Affiliated Lecturer
Contact
About
I am an Affiliated Lecturer at the Language Technology Lab (LTL), University of Cambridge, and a Research Associate at the Oxford Internet Institute (OII), University of Oxford.
My research is at the forefront of Natural Language Processing (NLP) and Large Language Models (LLMs), with a specialized focus on Explainability (XAI), algorithmic fairness, and the intersection of LLM and machine learning theory. I am dedicated to improving the stability, transparency, and trustworthiness of generative AI systems through both rigorous theoretical analysis and interdisciplinary application.
Previously, I was a Postdoctoral Researcher at both Cambridge and Oxford, collaborating with Prof. Nigel Collier, Prof. Chris Russell, and Prof. Sandra Wachter to advance the frontiers of machine learning policy, ethical AI, and interpretable model architectures.
Research
Education & Research Experience
2024 – Present | Research Associate Oxford Internet Institute, University of Oxford Focusing on LLM Explainability, Algorithmic Fairness, LLM Policy, and Model Evaluation.
2021 – 2024 | Postdoctoral Researcher & Affiliated Lecturer Language Technology Lab, Trinity College, University of Cambridge Focusing on LLM Interpretability, Text Generation, Biomedical NLP, and Parameter-Efficient Fine-Tuning.
2017 – 2021 | Ph.D. in Systems Engineering The Chinese University of Hong Kong Advisor: Prof. Wai Lam. Focus: Open Domain Text Generation.
2012 – 2015 | M.E. Beihang University (BUAA)
2008 – 2012 | B.E. Beihang University (BUAA)
Selected Publications
Trustworthy AI, Explainability & Fairness
FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models NeurIPS 2025 | Zihao Fu, Ryan Brown, Shun Shao, Kai Rawal, Eoin Delaney, Chris Russell.
Evaluating Model Explanations without Ground Truth FAccT 2025 | Kaivalya Rawal, Zihao Fu, Eoin Delaney, Chris Russell.
OxonFair: A Flexible Toolkit for Algorithmic Fairness NeurIPS 2024 | Eoin Delaney, Zihao Fu, Sandra Wachter, Brent Mittelstadt, Chris Russell.
LLM Stability, Efficiency & Interpretability
Decoder-Only or Encoder-Decoder? Interpreting Language Model as a Regularized Encoder-Decoder Preprint (2023) | Zihao Fu, Wai Lam, Qian Yu, Anthony Man-Cho So, Shengding Hu, Zhiyuan Liu, Nigel Collier.
BAND: Biomedical Alert News Dataset AAAI 2024 | Zihao Fu, Meiru Zhang, Zaiqiao Meng, Yannan Shen, David Buckeridge, Nigel Collier.
On the Effectiveness of Parameter-Efficient Fine-Tuning AAAI 2023 | Zihao Fu, Haoran Yang, Anthony Man-Cho So, Wai Lam, Lidong Bing, Nigel Collier.
Foundational NLP Theory
A Theoretical Analysis of the Repetition Problem in Text Generation AAAI 2021 | Zihao Fu, Wai Lam, Anthony Man-Cho So, Bei Shi.
Partially-Aligned Data-to-Text Generation with Distant Supervision EMNLP 2020 | Zihao Fu, Bei Shi, Wai Lam, Lidong Bing, Zhiyuan Liu.
Teaching and supervision
Affiliated Lecturer, Faculty of Modern and Medieval Languages and Linguistics, University of Cambridge.
Guest Lecturer, Li18: Computational Linguistics (2022-2023), University of Cambridge.
Academic Service (Reviewer): ACL, EMNLP, NeurIPS, ICLR, ICML, AAAI, TKDE.