Sebastian Farquhar

49 papers A* 11A 3Journal 34Unranked 1

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	An Approach to Technical AGI Safety and Security. CoRR Rohin Shah, Alex Irpan, Alexander Matt Turner, Anna Wang, Arthur Conmy, David Lindner, Jonah Brown-Cohen, Lewis Ho, Neel Nanda, Raluca Ada Popa, Rishub Jain, Rory Greig, Samuel Albanie, Scott Emmons, Sebastian Farquhar, Sébastien Krier, Senthooran Rajamanoharan, Sophie Bridgers, Tobi Ijitoye, Tom Everitt, Victoria Krakovna, Vikrant Varma, Vladimir Mikulik, Zachary Kenton, Dave Orr, Shane Legg, Noah D. Goodman, Allan Dafoe, Four Flynn, Anca D. Dragan
2025	J	`jnl`	Do Multilingual LLMs Think In English? CoRR Lisa Schut, Yarin Gal, Sebastian Farquhar
2025	A*	`conf`	MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking. ICML Sebastian Farquhar, Vikrant Varma, David Lindner, David Elson, Caleb Biddulph, Ian Goodfellow, Rohin Shah
2025	J	`jnl`	MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking. CoRR Sebastian Farquhar, Vikrant Varma, David Lindner, David K. Elson, Caleb Biddulph, Ian Goodfellow, Rohin Shah
2025	J	`jnl`	Practical challenges of control monitoring in frontier AI deployments. CoRR David Lindner, Charlie Griffin, Tomek Korbak, Roland S. Zimmermann, Geoffrey Irving, Sebastian Farquhar, Alan Cooney
2024	J	`jnl`	Detecting hallucinations in large language models using semantic entropy. Nat. Sebastian Farquhar, Jannik Kossen, Lorenz Kuhn, Yarin Gal
2024	A*	`conf`	Discovering Agents (Abstract Reprint). AAAI Zachary Kenton, Ramana Kumar, Sebastian Farquhar, Jonathan Richens, Matt MacDermott, Tom Everitt
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
2024	J	`jnl`	Holistic Safety and Responsibility Evaluations of Advanced AI Models. CoRR Laura Weidinger, Joslyn Barnhart, Jenny Brennan, Christina Butterfield, Susie Young, Will Hawkins, Lisa Anne Hendricks, Ramona Comanescu, Oscar Chang, Mikel Rodriguez, Jennifer Beroshi, Dawn Bloxwich, Lev Proleev, Jilin Chen, Sebastian Farquhar, Lewis Ho, Iason Gabriel, Allan Dafoe, William Isaac
2023	J	`jnl`	Challenges with unsupervised LLM knowledge discovery. CoRR Sebastian Farquhar, Vikrant Varma, Zachary Kenton, Johannes Gasteiger, Vladimir Mikulik, Rohin Shah
2023	J	`jnl`	Discovering agents. Artif. Intell. Zachary Kenton, Ramana Kumar, Sebastian Farquhar, Jonathan Richens, Matt MacDermott, Tom Everitt
2023	A	`conf`	Do Bayesian Neural Networks Need To Be Fully Stochastic? AISTATS Mrinank Sharma, Sebastian Farquhar, Eric T. Nalisnick, Tom Rainforth
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
2023	A	`conf`	Prediction-Oriented Bayesian Active Learning. AISTATS Freddie Bickford Smith, Andreas Kirsch, Sebastian Farquhar, Yarin Gal, Adam Foster, Tom Rainforth
2023	J	`jnl`	Prediction-Oriented Bayesian Active Learning. CoRR Freddie Bickford Smith, Andreas Kirsch, Sebastian Farquhar, Yarin Gal, Adam Foster, Tom Rainforth
2023	A*	`conf`	Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation. ICLR Lorenz Kuhn, Yarin Gal, Sebastian Farquhar
2023	J	`jnl`	Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation. CoRR Lorenz Kuhn, Yarin Gal, Sebastian Farquhar
2023	J	`jnl`	Stochastic Batch Acquisition: A Simple Baseline for Deep Active Learning. Trans. Mach. Learn. Res. Andreas Kirsch, Sebastian Farquhar, Parmida Atighehchian, Andrew Jesson, Frédéric Branchaud-Charron, Yarin Gal
2023	A*	`conf`	Tracr: Compiled Transformers as a Laboratory for Interpretability. NeurIPS David Lindner, János Kramár, Sebastian Farquhar, Matthew Rahtz, Tom McGrath, Vladimir Mikulik
2022	A*	`conf`	Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation. NeurIPS Jannik Kossen, Sebastian Farquhar, Yarin Gal, Thomas Rainforth
2022	J	`jnl`	Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation. CoRR Jannik Kossen, Sebastian Farquhar, Yarin Gal, Tom Rainforth
2022	J	`jnl`	CLAM: Selective Clarification for Ambiguous Questions with Large Language Models. CoRR Lorenz Kuhn, Yarin Gal, Sebastian Farquhar
2022	J	`jnl`	Discovering Agents. CoRR Zachary Kenton, Ramana Kumar, Sebastian Farquhar, Jonathan Richens, Matt MacDermott, Tom Everitt
2022	J	`jnl`	Do Bayesian Neural Networks Need To Be Fully Stochastic? CoRR Mrinank Sharma, Sebastian Farquhar, Eric T. Nalisnick, Tom Rainforth
2022	A*	`conf`	Path-Specific Objectives for Safer Agent Incentives. AAAI Sebastian Farquhar, Ryan Carey, Tom Everitt
2022	J	`jnl`	Path-Specific Objectives for Safer Agent Incentives. CoRR Sebastian Farquhar, Ryan Carey, Tom Everitt
2022	J	`jnl`	Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt. CoRR Sören Mindermann, Jan Markus Brauner, Muhammed Razzak, Mrinank Sharma, Andreas Kirsch, Winnie Xu, Benedikt Höltgen, Aidan N. Gomez, Adrien Morisot, Sebastian Farquhar, Yarin Gal
2022	A*	`conf`	Prioritized Training on Points that are Learnable, Worth Learning, and not yet Learnt. ICML Sören Mindermann, Jan Markus Brauner, Muhammed Razzak, Mrinank Sharma, Andreas Kirsch, Winnie Xu, Benedikt Höltgen, Aidan N. Gomez, Adrien Morisot, Sebastian Farquhar, Yarin Gal
2022	A*	`conf`	Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients. ICLR Milad Alizadeh, Shyam A. Tailor, Luisa M. Zintgraf, Joost van Amersfoort, Sebastian Farquhar, Nicholas Donald Lane, Yarin Gal
2022	J	`jnl`	Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients. CoRR Milad Alizadeh, Shyam A. Tailor, Luisa M. Zintgraf, Joost van Amersfoort, Sebastian Farquhar, Nicholas Donald Lane, Yarin Gal
2022	J	`jnl`	Understanding Approximation for Bayesian Inference in Neural Networks. CoRR Sebastian Farquhar
2021	J	`jnl`	A Simple Baseline for Batch Active Learning with Stochastic Acquisition Functions. CoRR Andreas Kirsch, Sebastian Farquhar, Yarin Gal
2021	A*	`conf`	Active Testing: Sample-Efficient Model Evaluation. ICML Jannik Kossen, Sebastian Farquhar, Yarin Gal, Tom Rainforth
2021	J	`jnl`	Active Testing: Sample-Efficient Model Evaluation. CoRR Jannik Kossen, Sebastian Farquhar, Yarin Gal, Tom Rainforth
2021	—	`conf`	Evaluating Approximate Inference in Bayesian Deep Learning. NeurIPS (Competition and Demos) Andrew Gordon Wilson, Pavel Izmailov, Matthew D. Hoffman, Yarin Gal, Yingzhen Li, Melanie F. Pradier, Sharad Vikram, Andrew Y. K. Foong, Sanae Lotfi, Sebastian Farquhar
2021	J	`jnl`	On Statistical Bias In Active Learning: How and When To Fix It. CoRR Sebastian Farquhar, Yarin Gal, Tom Rainforth
2021	A*	`conf`	On Statistical Bias In Active Learning: How and When to Fix It. ICLR Sebastian Farquhar, Yarin Gal, Tom Rainforth
2021	J	`jnl`	Prioritized training on points that are learnable, worth learning, and not yet learned. CoRR Sören Mindermann, Muhammed Razzak, Winnie Xu, Andreas Kirsch, Mrinank Sharma, Adrien Morisot, Aidan N. Gomez, Sebastian Farquhar, Jan Markus Brauner, Yarin Gal
2021	J	`jnl`	Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning. CoRR Zachary Nado, Neil Band, Mark Collier, Josip Djolonga, Michael W. Dusenberry, Sebastian Farquhar, Angelos Filos, Marton Havasi, Rodolphe Jenatton, Ghassen Jerfel, Jeremiah Z. Liu, Zelda Mariet, Jeremy Nixon, Shreyas Padhy, Jie Ren, Tim G. J. Rudner, Yeming Wen, Florian Wenzel, Kevin Murphy, D. Sculley, Balaji Lakshminarayanan, Jasper Snoek, Yarin Gal, Dustin Tran
2020	A*	`conf`	Liberty or Depth: Deep Bayesian Neural Nets Do Not Need Complex Weight Posterior Approximations. NeurIPS Sebastian Farquhar, Lewis Smith, Yarin Gal
2020	A	`conf`	Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning. AISTATS Sebastian Farquhar, Michael A. Osborne, Yarin Gal
2020	J	`jnl`	Single Shot Structured Pruning Before Training. CoRR Joost van Amersfoort, Milad Alizadeh, Sebastian Farquhar, Nicholas D. Lane, Yarin Gal
2020	J	`jnl`	Try Depth Instead of Weight Correlations: Mean-field is a Less Restrictive Assumption for Deeper Networks. CoRR Sebastian Farquhar, Lewis Smith, Yarin Gal
2019	J	`jnl`	A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks. CoRR Angelos Filos, Sebastian Farquhar, Aidan N. Gomez, Tim G. J. Rudner, Zachary Kenton, Lewis Smith, Milad Alizadeh, Arnoud de Kroon, Yarin Gal
2019	J	`jnl`	A Unifying Bayesian View of Continual Learning. CoRR Sebastian Farquhar, Yarin Gal
2019	J	`jnl`	Differentially Private Continual Learning. CoRR Sebastian Farquhar, Yarin Gal
2019	J	`jnl`	Radial Bayesian Neural Networks: Robust Variational Inference In Big Models. CoRR Sebastian Farquhar, Michael A. Osborne, Yarin Gal
2018	J	`jnl`	The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation. CoRR Miles Brundage, Shahar Avin, Jack Clark, Helen Toner, Peter Eckersley, Ben Garfinkel, Allan Dafoe, Paul Scharre, Thomas Zeitzoff, Bobby Filar, Hyrum S. Anderson, Heather Roff, Gregory C. Allen, Jacob Steinhardt, Carrick Flynn, Seán Ó hÉigeartaigh, Simon Beard, Haydn Belfield, Sebastian Farquhar, Clare Lyle, Rebecca Crootof, Owain Evans, Michael Page, Joanna Bryson, Roman Yampolskiy, Dario Amodei
2018	J	`jnl`	Towards Robust Evaluations of Continual Learning. CoRR Sebastian Farquhar, Yarin Gal