Mary Phuong

16 papers A* 4Journal 12
YearRankTypeTitle / Venue / Authors
2026 J jnl
Phantom Transfer: Data-level Defences are Insufficient Against Data Poisoning.
CoRR
Andrew Draganov, Tolga H. Dur, Anandmayi Bhongade, Mary Phuong
2025 J jnl
Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety.
CoRR
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
2025 J jnl
CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring.
CoRR
Benjamin Arnav, Pablo Bernabeu-Perez, Nathan Helm-Burger, Tim Kostolansky, Hannes Whittingham, Mary Phuong
2025 J jnl
Evaluating Frontier Models for Stealth and Situational Awareness.
CoRR
Mary Phuong, Roland S. Zimmermann, Ziyue Wang, David Lindner, Victoria Krakovna, Sarah Cogan, Allan Dafoe, Lewis Ho, Rohin Shah
2025 J jnl
From Stability to Inconsistency: A Study of Moral Preferences in LLMs.
CoRR
Monika Jotautaite, Mary Phuong, Chatrik Singh Mangat, Maria Angelica Martinez
2025 J jnl
LLMs Can Covertly Sandbag on Capability Evaluations Against Chain-of-Thought Monitoring.
CoRR
Chloe Li, Mary Phuong, Noah Y. Siegel
2025 J jnl
Spilling the Beans: Teaching LLMs to Self-Report Their Hidden Objectives.
CoRR
Chloe Li, Mary Phuong, Daniel Tan
2024 J jnl
Evaluating Frontier Models for Dangerous Capabilities.
CoRR
Mary Phuong, Matthew Aitchison, Elliot Catt, Sarah Cogan, Alexandre Kaskasoli, Victoria Krakovna, David Lindner, Matthew Rahtz, Yannis Assael, Sarah Hodkinson, Heidi Howard, Tom Lieberum, Ramana Kumar, Maria Abi Raad, Albert Webson, Lewis Ho, Sharon Lin, Sebastian Farquhar, Marcus Hutter, Grégoire Delétang, Anian Ruoss, Seliem El-Sayed, Sasha Brown, Anca D. Dragan, Rohin Shah, Allan Dafoe, Toby Shevlane
2023 J jnl
Model evaluation for extreme risks.
CoRR
Toby Shevlane, Sebastian Farquhar, Ben Garfinkel, Mary Phuong, Jess Whittlestone, Jade Leung, Daniel Kokotajlo, Nahema Marchal, Markus Anderljung, Noam Kolt, Lewis Ho, Divya Siddarth, Shahar Avin, Will Hawkins, Been Kim, Iason Gabriel, Vijay Bolina, Jack Clark, Yoshua Bengio, Paul F. Christiano, Allan Dafoe
2022 J jnl
Formal Algorithms for Transformers.
CoRR
Mary Phuong, Marcus Hutter
2022 J jnl
Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals.
CoRR
Rohin Shah, Vikrant Varma, Ramana Kumar, Mary Phuong, Victoria Krakovna, Jonathan Uesato, Zac Kenton
2021 A* conf
The inductive bias of ReLU networks on orthogonally separable data.
ICLR
Mary Phuong, Christoph H. Lampert
2021 J jnl
Towards Understanding Knowledge Distillation.
CoRR
Mary Phuong, Christoph H. Lampert
2020 A* conf
Functional vs. parametric equivalence of ReLU networks.
ICLR
Mary Phuong, Christoph H. Lampert
2019 A* conf
Distillation-Based Training for Multi-Exit Architectures.
ICCV
Mary Phuong, Christoph Lampert
2019 A* conf
Towards Understanding Knowledge Distillation.
ICML
Mary Phuong, Christoph Lampert