About Me
I am Cass Zhixue Zhao, a lecturer (Assistant Professor) in Natural Language Processing at the Computer Science Department of the University of Sheffield. My long-term research goal is to enable trustworthy, responsible, and efficient NLP models. These days, I am interested in anything related to interpretability and large language models (LLMs). My recent research projects focus on model compression, model editing, and text-to-image models. Previously, I served as co-Principal Investigator on the ExU project, developing multilingual AI tools to support journalists and fact-checkers in identifying disinformation narratives.
Previously, I worked as a Postdoc researcher on explainable AI and responsible AI. The overarching aim is to demystify predictions made by black-box LLMs, making them easier to understand and trustworthy. The work also addresses model hallucination to ensure the reliability of LLMs, alongside exploring model compression techniques that mitigate compute demands and thus foster inclusivity within NLP research. Back in 2020, I worked as a research assistant within the same department, working on NIHR-funded NLP projects for systematic reviews of public health research. My Ph.D. research, funded by the University of Sheffield, examined transfer learning and mitigating model bias in hate speech detection.
Test Test🚀 A fully funded PhD studentship @SheffieldNLP. Join us to explore cutting-edge topics in AI safety and Generative AI integrity 🧠✨ Get in touch if you’d like to chat about the PhD, our research, or life in Sheffield! Also, one UK home standard studentship is available in 2027.
📩 If you’re considering self-funding or already have external funding, please feel free to contact me with your CV. Visiting students are also very welcome!
Test TestSelected Publications in 2025
ICML2025 Rulebreakers Challenge: Revealing a Blind Spot in Large Language Models’ Reasoning with Formal Logic.
Jason Chan, Robert Gaizauskas, Zhixue Zhao
ICML2025 Position: Editing Large Language Models Poses Serious Safety Risks.
Paul Youssef, Zhixue Zhao, Daniel Braun, Jörg Schlötterer, Christin Seifert
ICLR2025 ScImage: How good are multimodal large language models at scientific text-to-image generation?
Leixin Zhang, Yinjie Cheng, Weihe Zhai, Steffen Eger, Jonas Belouadi, Fahimeh Moafian, Zhixue Zhao.
TACL2025 Investigating Language-Specific Calibration for Pruning Multilingual Large Language Models
Simon Kurz, Jian-Jia Chen, Lucie Flek, Zhixue Zhao
ICWSM26 SCRum-9: Multilingual Stance Classification over Rumours on Social Media
Yue Li, Jake Vasilakes, Zhixue Zhao, Carolina Scarton
AAAI26 Oral Mitigating Content Effects on Reasoning in Language Models through Fine-Grained Activation Steering
Marco Valentino, Geonhee Kim, Dhairya Dalal, Zhixue Zhao, Andre Freitas
AAAI2026 Poster Making Visual Dialogue More Engaging: A New Task, Method, and Metric
Guanghui Ye, Huan Zhao, Yingxue Gao, Zhixue Zhao, Kehan Wang, Xupeng Zha, Zhihua Jiang
EMNLP2025 Main Minimal, Local, and Robust: Embedding-Only Edits for Implicit Bias in T2I Models
Feng He, Chao Zhang, Zhixue Zhao
EMNLP2025 Main Oral Top15% Label Set Optimization via Activation Distribution Kurtosis for Zero-Shot Classification with Generative Models
Yue Li, Zhixue Zhao, Carolina Scarton
EMNLP2025 Main It’s All About In-Context Learning! Teaching Extremely Low-Resource Languages to LLMs
Yue Li, Zhixue Zhao, Carolina Scarton
EMNLP2025 Findings Revisiting Pruning vs Quantization for Small Language Models
Zihan Zhou, Simon Kurz, Zhixue Zhao
EMNLP2025 Main Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?
Samuel Lewis-Lim, Xingwei Tan, Zhixue Zhao, Nikolaos Aletras
ACL2025 Main. Knowledge Image Matters: Improving Knowledge-Based Visual Reasoning with Multi-Image Large Language Models
Guanghui Ye, Huan Zhao, Zhixue Zhao, Xupeng Zha, Yang Liu, Zhihua Jiang
ACL2025 Findings Explainable Hallucination through Natural Language Inference Mapping
Wei-Fan Chen, Zhixue Zhao, Akbar Karimi, Lucie Flek
Knowledge-Based Systems 2025 AI-generated content in cross-domain applications: Research trends, challenges and propositions
Jianxin Li, Liang Qu, Taotao Cai, Zhixue Zhao, Nur Al Hasan Haldar, Aneesh Krishna, Xiangjie Kong, Flavio Romero Macau, Tanmoy Chakraborty, Aniket Deroy, Binshan Lin, Karen Blackmore, Nasimul Noman, Jingxian Cheng, Ningning Cui, Jianliang Xu
IEEE Transactions on Computational Social Systems CCDE: A Compact and Competitive Dialogue Evaluation Framework via Knowledge Distillation of Large Language Models
Guanghui Ye; Huan Zhao; Bo Li; Haijiao Chen; Zhixue Zhao; Zhihua Jiang
NAACL2025 Main How to Make LLMs Forget: On Reversing In-Context Knowledge Edits
Paul Youssef, Zhixue Zhao, Jörg Schlötterer, Christin Seifert.
NAACL2025 Main Oral Has this Fact been Edited? Detecting Knowledge Edits in Language Models?
Paul Youssef, Zhixue Zhao, Jörg Schlötterer, Christin Seifert.
(More papers in publications.)
TestProject
- Co-PI of ExU