Geoffrey Irving

Chief Scientist, UK AI Security Institute

Joined

April 2020

Names

Geoffrey Irving (Preferred)

Emails

****@google.com (Confirmed)

****@naml.us (Confirmed)

****@deepmind.com (Confirmed)

****@openai.com

****@dsit.gov.uk (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Chief Scientist

UK AI Security Institute (aisi.gov.uk)

2024 – Present

Safety Researcher

DeepMind (deepmind.com)

2019 – 2024

Safety Researcher

OpenAI (openai.com)

2017 – 2019

Software Engineer

Google Brain (google.com)

2015 – 2017

Advisors, Relations & Conflicts

PhD Advisor

Ron Fedkiw

2003 – 2007

Expertise

AI safety

AGI safety

AI alignment

reward learning

Present

theorem proving

Present

Publications

Practical challenges of control monitoring in frontier AI deployments
David Lindner, Charlie Griffin, Tomek Korbak, Roland S. Zimmermann, Geoffrey Irving, Sebastian Farquhar, Alan Cooney
- OpenReview Archive Direct Upload
- Readers: Everyone
Open Technical Problems in Open-Weight AI Model Risk Management
Stephen Casper, Kyle O'Brien, Shayne Longpre, Elizabeth Seger, Kevin Klyman, Rishi Bommasani, Aniruddha Nrusimha, Ilia Shumailov, Sören Mindermann, Steven Basart, Frank Rudzicz, Kellin Pelrine, Avijit Ghosh, Andrew Strait, Robert Kirk, Dan Hendrycks, Peter Henderson, J Zico Kolter, Geoffrey Irving, Yarin Gal et al. (2 additional authors not shown)
- Accepted by TMLR
- Readers: Everyone
Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
Kyle O'Brien, Stephen Casper, Quentin Gregory Anthony, Tomek Korbak, Robert Kirk, Xander Davies, Ishan Mishra, Geoffrey Irving, Yarin Gal, Stella Biderman
- ICLR 2026 Poster
- Readers: Everyone
Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
Kyle O'Brien, Stephen Casper, Quentin Gregory Anthony, Tomek Korbak, Robert Kirk, Xander Davies, Ishan Mishra, Geoffrey Irving, Yarin Gal, Stella Biderman
- BioSafe GenAI 2025 Oral
- Readers: Everyone
Scalable AI Safety via Doubly-Efficient Debate
Jonah Brown-Cohen, Geoffrey Irving, Georgios Piliouras
- Agentic Markets @ ICML'24 Oral
- Readers: Everyone
Scalable AI Safety via Doubly-Efficient Debate
Jonah Brown-Cohen, Geoffrey Irving, Georgios Piliouras
- ICML 2024 Oral
- Readers: Everyone
Scalabale AI Safety via Doubly-Efficient Debate
Jonah Brown-Cohen, Geoffrey Irving, Georgios Piliouras
- Submitted to ICLR 2024
- Readers: Everyone
Solving Math Word Problems with Process-based and Outcome-based Feedback
Jonathan Uesato, Nate Kushman, Ramana Kumar, H. Francis Song, Noah Yamamoto Siegel, Lisa Wang, Antonia Creswell, Geoffrey Irving, Irina Higgins
- Published: 01 Feb 2023, Last Modified: 13 Feb 2023
- Submitted to ICLR 2023
- Readers: Everyone
Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models
Maribeth Rauh, John F J Mellor, Jonathan Uesato, Po-Sen Huang, Johannes Welbl, Laura Weidinger, Sumanth Dathathri, Amelia Glaese, Geoffrey Irving, Iason Gabriel, William Isaac, Lisa Anne Hendricks
- Published: 17 Sept 2022, Last Modified: 08 Feb 2026
- NeurIPS 2022 Datasets and Benchmarks
- Readers: Everyone
Red Teaming Language Models with Language Models
Ethan Perez, Saffron Huang, H. Francis Song, Trevor Cai, Roman Ring, John Aslanides, Amelia Glaese, Nat McAleese, Geoffrey Irving
- 2022 (modified: 26 Feb 2022)
- CoRR 2022
- Readers: Everyone

View all 23 publications

Co-Authors

View all 176 co-authors