Zihao Fu is currently a Research Assistant Professor in the Department of Linguistics and Modern Languages at The Chinese University of Hong Kong. His research focuses on large language models, natural language processing, and their interdisciplinary applications. Prior to this, Zihao was a Postdoctoral Researcher at the Oxford Internet Institute, University of Oxford, and a Research Associate at the Language Technology Lab, University of Cambridge. He obtained his Ph.D. from The Chinese University of Hong Kong.

Zihao is particularly interested in the theoretical and practical challenges of large language models, including issues such as instability, repetition, and hallucination. His work seeks to bridge large language models and machine learning with theories and applications from the social sciences, including linguistics, cognitive science, and algorithmic fairness, with the goal of advancing both foundational understanding and real-world applications of language technologies.

• Large Language Model
• Natural Language Processing
• Machine Learning

Please check my recent publications for a better understanding of my research interests. Feel free to contact me via email if you have any questions or share similar interests in these research areas.

Eoin Delaney, Zihao Fu, Sandra Wachter, Brent Mittelstadt, Chris Russell OxonFair: A Flexible Toolkit for Algorithmic Fairness (NeurIPS 2024)
Zihao Fu, Meiru Zhang, Zaiqiao Meng, Yannan Shen, David Buckeridge, Nigel Collier. BAND: Biomedical Alert News Dataset. The 38th AAAI Conference on Artificial Intelligence (AAAI 2024).
Zihao Fu, Anthony Man-Cho So, Nigel Collier. A Stability Analysis of Fine-Tuning a Pre-Trained Model. PrePrint
Zihao Fu, Wai Lam, Qian Yu, Anthony Man-Cho So, Shengding Hu, Zhiyuan Liu, Nigel Collier. Decoder-Only or Encoder-Decoder? Interpreting Language Model as a Regularized Encoder-Decoder. PrePrint
Zihao Fu, Yixuan Su, Zaiqiao Meng, Nigel Collier. Biomedical Named Entity Recognition via Dictionary-based Synonym Generalization. The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023).
Zihao Fu, Haoran Yang, Anthony Man-Cho So, Wai Lam, Lidong Bing, Nigel Collier. On the Effectiveness of Parameter-Efficient Fine-Tuning. The 37th AAAI Conference on Artificial Intelligence (AAAI 2023).
Zihao Fu. Open Domain Text Generation. (PhD Thesis, The Chinese University of Hong Kong, 2021).
Zihao Fu, Wai Lam, Anthony Man-Cho So, Bei Shi. A Theoretical Analysis of the Repetition Problem in Text Generation. The 35th AAAI Conference on Artificial Intelligence (AAAI 2021).
Zihao Fu, Lidong Bing, Wai Lam. Open Domain Event Text Generation. The 34th AAAI Conference on Artificial Intelligence (AAAI 2020).
Zihao Fu, Bei Shi, Wai Lam, Lidong Bing, Zhiyuan Liu. Partially-Aligned Data-to-Text Generation with Distant Supervision. The 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020).
Zihao Fu, Lidong Bing, Wai Lam, Shoaib Jameel. Dynamic Topic Tracker for KB-to-Text Generation. The 28th International Conference on Computational Linguistics (COLING 2020).
Zihao Fu, Bei Shi, Lidong Bing, Wai Lam. Unsupervised KB-to-Text Generation with Auxiliary Triple Extraction using Dual Learning. The 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing (AACL-IJCNLP 2020).
Zihao Fu, Yankai Lin, Zhiyuan Liu, Wai Lam. Fact Discovery from Knowledge Base via Facet Decomposition. The 2019 Conference of the North American Chapter of the Association for Computational Linguistics – Human Language Technologies (NAACL-HLT 2019).
Shoaib Jameel, Zihao Fu, Bei Shi, Wai Lam, Steven Schockaert. Word Embedding as Maximum A Posteriori Estimation. The 33rd AAAI Conference on Artificial Intelligence (AAAI 2019).
Bei Shi, Zihao Fu, Lidong Bing, Wai Lam. Learning Domain-Sensitive and Sentiment-Aware Word Embeddings. The 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018).
Guo, Tszhang, Bowen Li, Zihao Fu, Tao Wan and Zengchang Qin. Learning Sentimental Weights of Mixed-gram Terms for Classification and Visualization. Pacific Rim International Conferences on Artificial Intelligence (PRICAI 2016).
Yanan Zhou, Zihao Fu, Guanghong Gong. Pilot Behavior Modeling Using LSTM Network: A Case Study. Asian Simulation Conference (ASC 2016).
Zihao Fu, Guanghong Gong. Explicit moment integration algorithm and its application. Journal of Beijing University of Aeronautics and Astronautics (JBUAA 2015).
Zihao Fu. Research on the Optimization Methods of the Blended-Wing-Body Aircraft. (Master Thesis 2015).