Adam Mahdi is an Associate Professor and Senior Research Fellow at the Oxford Internet Institute, and an associate member of St Antony’s College, Oxford. He is also a Fellow of Wolfson College and a Stipendiary Lecturer at Lady Margaret Hall.
He leads the Reasoning with Machines Lab, which focuses on the science of LLM evaluation, AI safety, agentic AI for science, and human–LLM interaction. His group combines mathematical rigour with empirical investigation to better understand how large language models process information, solve tasks, and interact with humans in real-world contexts.
Prior to joining the Oxford Internet Institute in 2021, Adam was a Research Fellow at the Institute of Biomedical Engineering in the Department of Engineering Science, University of Oxford; a Visiting Fellow at the Isaac Newton Institute for Mathematical Sciences, University of Cambridge; and a Research Assistant Professor at North Carolina State University.
LLM and agentic evaluations, AI safety, human-AI interaction
Media narratives on migration are perceived to have a significant impact on policy decisions and public attitudes toward migration. The project applies tools and methods to enable practitioners to make more effective policy decisions.
The Oxford COVID-19 Project aims to increase our understanding of COVID-19 and elaborate possible strategies to reduce the impact on the society through the combined power of Statistical, Mathematical Modelling and Machine Learning techniques.
A data-driven approach to understanding structural determinants of digital inequalities
25 November 2025
Researchers from the Oxford Internet Institute at the University of Oxford will be at NeurIPS 2025 in San Diego from 1- 7 December, 2025, contributing to one of the world’s leading AI conferences.
4 November 2025
Largest systematic review of AI benchmarks highlights need for clearer definitions and stronger scientific standards.
31 October 2025
Researchers, including those from the Oxford Internet Institute’s Reasoning with Machine’s Lab (OxRML), will attend the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP) in Suzhou, China from 4-9 November.
17 June 2025
Dr Adam Mahdi, Dr Ana Valdivia, Professor Greg Taylor, and Professor Kathryn Eccles are among the teaching faculty recognised for teaching excellence at Oxford.
New Scientist, 19 November 2025
Google’s latest model reportedly beats its rivals in several benchmark tests, but issues with reliability mean concerns remain over a possible AI bubble. Dr Luc Rocher and Dr Adam Mahdi comment.
New York Times, 16 November 2025
Chatbots are cheap, always available, superficially empathetic — and sometimes wrong. Some have concluded they’re a risk worth taking. Article references upcoming study from OII researchers.
NBC News, 09 November 2025
The NBC Morning News programme discuss the findings from latest OII study which finds weaknesses in how AI systems are evaluated.
DPhil Student
Djavan is a part-time DPhil student conducting research at the intersection of agriculture and climatic change. He is currently a consultant at McKinsey & Company.
DPhil Student
Felix is a DPhil student at the OII with an MSc in Industrial Engineering and Management, and has over 2 years of work experience as analytics consultant at McKinsey & Company.
DPhil Student
Andrew holds a B.S. in Applied Mathematics from Yale University and an MSc in Social Data Science from the OII. He is a Clarendon Scholar and was previously a Thouron Prize winner at the University of Cambridge (Pembroke College).
DPhil Student
Harry is a DPhil student at the OII working on explainability and interpretability in large language models.
DPhil Student
Jessica is a DPhil student in Social Data Science, researching the societal impact of research using NLP and knowledge graphs. She holds an MSc in Computer Science and works as a Lead Data Scientist.
DPhil Student
Guy is a Shirley Scholar at the OII, an Intensive Care doctor, and the Clinical Lead for a Health AI business at Deloitte. He researches AI-enabled healthcare systems.
DPhil Student
Yushi is a DPhil student in Social Data Science at the OII, and an aspiring data scientist. Her research focuses on developing interpretability methods to improve safety mechanisms in large language models and ensure robust harm mitigation.
DPhil Student
Karolina is a DPhil student in Social Data Science and a Clarendon Scholar at the OII. Her research focuses on the societal impacts of advanced AI systems.
DPhil Student
Ryan is a Clarendon Scholar and a member of the Reasoning with Machines Lab at the OII. He studies the cognitive capabilities of large language models.
DPhil Student
Karolina is a DPhil student in Social Data Science and a Clarendon Scholar at the OII. Her research focuses on the societal impacts of advanced AI systems.
Former MSc Student
Khyati has completed her Bachelor’s in Statistics and Mathematics from the University of Mumbai. She has full time, as well as internship experience in text Analytics, NLP and Machine Learning.
Former MSc Student
Henry holds a BA in PPE from the University of Oxford. He is interested in using data science methods to understand the media's influence on politics, voting for radical parties, and elite behaviour.
Former MSc Student
Sneha holds a BSc in Economics and Finance from Exeter University. Sneha is interested leveraging machine learning techniques to model and foresee climate action outcomes in developing nations. Sneha also has a passion for quantitative finance.
Former MSc Student
Mehdi holds a degree in Statistics from Williams College. He spent two undergraduate years at the University of Oxford studying machine learning, Islamic studies, and Middle Eastern studies.
Former MSc Student
Saskia holds a BSc in Mathematics and Statistics. Prior to her postgraduate studies, she worked as Data Scientist in the financial sector.
Former MSc Student
Adam completed a MA in Japanese and Linguistics at the University of Edinburgh and has experience working as a translator. Adam is interested in applying natural language processing to examine the sociolinguistics of the internet.
This course teaches practical and applied Machine Learning techniques, focusing on how to apply the mathematical foundations of machine learning to domains where we are uncertain about the right answer or best approach, with an emphasis on temporal and graph-based approaches.
