Fabien Roger

According to our database, Fabien Roger authored at least 19 papers between 2023 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Self-Attribution Bias: When AI Monitors Go Easy on Themselves.

Dipika Khullar, Jack Hopkins, Rowan Wang, Fabien Roger

CoRR, March, 2026

Three Concrete Challenges and Two Hopes for the Safety of Unsupervised Elicitation.

Callum Canavan, Aditya Shrivastava, Allison Qi, Jonathan Michala, Fabien Roger

CoRR, February, 2026

Excess Description Length of Learning Generalizable Predictors.

Elizabeth Donoway, Hailey Joren, Fabien Roger, Jan Leike

CoRR, January, 2026

2025

Steering Language Models with Weight Arithmetic.

Constanza Fierro, Fabien Roger

CoRR, November, 2025

All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Language.

Shiyuan Guo, Henry Sleight, Fabien Roger

CoRR, October, 2025

Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment.

Nevan Wichers, Aram Ebtekar, Ariana Azarbal, Victor Gillioz, Christine Ye, Emil Ryd, Neil Rathi, Henry Sleight, Alex Mallen, Fabien Roger, Samuel Marks

CoRR, October, 2025

Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety.

Tomek Korbak, Mikita Balesni, Elizabeth Barnes, Yoshua Bengio, Joe Benton, Joseph Bloom, Mark Chen, Alan Cooney, Allan Dafoe, Anca D. Dragan, Scott Emmons, Owain Evans, David Farhi, Ryan Greenblatt, Dan Hendrycks, Marius Hobbhahn, Evan Hubinger, Geoffrey Irving, Erik Jenner, Daniel Kokotajlo, Victoria Krakovna, Shane Legg, David Lindner, David Luan, Aleksander Madry, Julian Michael, Neel Nanda, Dave Orr, Jakub Pachocki, Ethan Perez, Mary Phuong, Fabien Roger, Joshua Saxe, Buck Shlegeris, Martín Soto, Eric Steinberger, Jasmine Wang, Wojciech Zaremba, Bowen Baker, Rohin Shah, Vladimir Mikulik

CoRR, July, 2025

Why Do Some Language Models Fake Alignment While Others Don't?

Abhay Sheshadri, John Hughes, Julian Michael, Alex Mallen, Arun Jose, Janus, Fabien Roger

CoRR, June, 2025

Reasoning Models Don't Always Say What They Think.

Yanda Chen, Joe Benton, Ansh Radhakrishnan, Jonathan Uesato, Carson Denison, John Schulman, Arushi Somani, Peter Hase, Misha Wagner, Fabien Roger, Vladimir Mikulik, Samuel R. Bowman, Jan Leike, Jared Kaplan, Ethan Perez

CoRR, May, 2025

Auditing language models for hidden objectives.

Samuel Marks, Johannes Treutlein, Trenton Bricken, Jack Lindsey, Jonathan Marcus, Siddharth Mishra-Sharma, Daniel M. Ziegler, Emmanuel Ameisen, Joshua Batson, Tim Belonax, Samuel R. Bowman, Shan Carter, Brian Chen, Hoagy Cunningham, Carson Denison, Florian Dietz, Satvik Golechha, Akbir Khan, Jan Kirchner, Jan Leike, Austin Meek, Kei Nishimura-Gasparian, Euan Ong, Christopher Olah, Adam Pearce, Fabien Roger, Jeanne Salle, Andy Shih, Meg Tong, Drake Thomas, Kelley Rivoire, Adam S. Jermyn, Monte MacDiarmid, Tom Henighan, Evan Hubinger

CoRR, March, 2025

A Frontier AI Risk Management Framework: Bridging the Gap Between Current AI Practices and Established Risk Management.

Siméon Campos, Henry Papadatos, Fabien Roger, Chloé Touzet, Otter Quarks, Malcolm Murray

CoRR, February, 2025

2024

Language Models Are Better Than Humans at Next-token Prediction.

Buck Shlegeris, Fabien Roger, Lawrence Chan, Euan McLean

Trans. Mach. Learn. Res., 2024

Alignment faking in large language models.

Ryan Greenblatt, Carson Denison, Benjamin Wright, Fabien Roger, Monte MacDiarmid, Samuel Marks, Johannes Treutlein, Tim Belonax, Jack Chen, David Duvenaud, Akbir Khan, Julian Michael, Sören Mindermann, Ethan Perez, Linda Petrini, Jonathan Uesato, Jared Kaplan, Buck Shlegeris, Samuel R. Bowman, Evan Hubinger

CoRR, 2024

Do Unlearning Methods Remove Information from Language Model Weights?

Aghyad Deeb, Fabien Roger

CoRR, 2024

Stress-Testing Capability Elicitation With Password-Locked Models.

Ryan Greenblatt, Fabien Roger, Dmitrii Krasheninnikov, David Krueger

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

AI Control: Improving Safety Despite Intentional Subversion.

Ryan Greenblatt, Buck Shlegeris, Kshitij Sachan, Fabien Roger

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

Preventing Language Models From Hiding Their Reasoning.

Fabien Roger, Ryan Greenblatt

CoRR, 2023

Measurement Tampering Detection Benchmark.

Fabien Roger, Ryan Greenblatt, Max Nadeau, Buck Shlegeris, Nate Thomas

CoRR, 2023

Large Language Models Sometimes Generate Purely Negatively-Reinforced Text.

Fabien Roger

CoRR, 2023