Adam Mahdi

Associate Professor, University of Oxford

Joined

October 2023

Names

Adam Mahdi (Preferred)

Emails

****@oii.ox.ac.uk (Confirmed)

Personal Links

Homepage

Google Scholar

Career & Education History

Associate Professor

University of Oxford (ox.ac.uk)

2021 – Present

Advisors, Relations & Conflicts

No relations added

Expertise

Large Language Models

2020 – Present

Machine Learning

2016 – Present

Publications

A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior
Harry Mayne, Justin Singh Kang, Dewi Sid William Gould, Kannan Ramchandran, Adam Mahdi, Noah Y. Siegel
- ICLR 2026 Trustworthy AI
- Readers: Everyone
LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations
Harry Mayne, Ryan Othniel Kearns, Yushi Yang, Andrew M. Bean, Eoin D. Delaney, Chris Russell, Adam Mahdi
- EMNLP
- Readers: Everyone
To Distill or Not to Distill: Knowledge Transfer Undermines Safety of LLMs
Shreyansh Padarha, Yushi Yang, Adel Bibi, Chris Russell, Adam Mahdi
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents
Karolina Korgul, Yushi Yang, Arkadiusz Drohomirecki, Piotr Blaszczyk, Will Howard, Lukas Aichberger, Chris Russell, Philip Torr, Adam Mahdi, Adel Bibi
- Submitted to ICLR 2026
- Readers: Everyone
Agentic reinforcement learning for search is unsafe
Yushi Yang, Shreyansh Padarha, Andrew Lee, Adam Mahdi
- Submitted to ICLR 2026
- Readers: Everyone
LINGOLY-TOO: Disentangling Reasoning from Knowledge with Templatised Orthographic Obfuscation
Jude Khouja, Lingyi Yang, Karolina Korgul, Simeon Hellsten, Vlad A. Neacșu, Harry Mayne, Ryan Othniel Kearns, Andrew M. Bean, Adam Mahdi
- ICLR 2026 Poster
- Readers: Everyone
Evaluating LLM-as-a-Judge under Multilingual, Multimodal and Multi-domain Constraints
Shreyansh Padarha, Elizaveta Semenova, Bertie Vidgen, Adam Mahdi, Scott A. Hale
- NeurIPS 2025 LLM Evaluation Workshop Poster
- Readers: Everyone
Measuring what Matters: Construct Validity in Large Language Model Benchmarks
Andrew M. Bean, Ryan Othniel Kearns, Angelika Romanou, Franziska Sofia Hafner, Harry Mayne, Jan Batzner, Negar Foroutan, Chris Schmitz, Karolina Korgul, Hunar Batra, Oishi Deb, Emma Beharry, Cornelius Emde, Thomas Foster, Anna Gausen, María Grandury, Simeng Han, Valentin Hofmann, Lujain Ibrahim, Hazel Kim et al. (22 additional authors not shown)
- NeurIPS 2025 Datasets and Benchmarks Track poster
- Readers: Everyone
Evaluating Fine-Tuning Efficiency of Human-Inspired Learning Strategies in Medical Question Answering
Yushi Yang, Andrew Michael Bean, Robert McCraith, Adam Mahdi
- FITML 2024 Poster
- Readers: Everyone
Improving In-Context Learning with Small Language Model Ensembles
M. Mehdi Mojarradi, Lingyi Yang, Robert McCraith, Adam Mahdi
- AFM 2024 Poster
- Readers: Everyone

View all 16 publications

Co-Authors

View all 65 co-authors