Owain Evans
Owain Evans
Research Associate, University of Oxford
Verified email at - Homepage
Cited by
Cited by
The malicious use of artificial intelligence: Forecasting, prevention, and mitigation
M Brundage, S Avin, J Clark, H Toner, P Eckersley, B Garfinkel, A Dafoe, ...
arXiv preprint arXiv:1802.07228, 2018
When will AI exceed human performance? Evidence from AI experts
K Grace, J Salvatier, A Dafoe, B Zhang, O Evans
Journal of Artificial Intelligence Research 62, 729-754, 2018
Beyond the imitation game: Quantifying and extrapolating the capabilities of language models
A Srivastava, A Rastogi, A Rao, AAM Shoeb, A Abid, A Fisch, AR Brown, ...
arXiv preprint arXiv:2206.04615, 2022
Truthfulqa: Measuring how models mimic human falsehoods
S Lin, J Hilton, O Evans
arXiv preprint arXiv:2109.07958, 2021
Trial without error: Towards safe reinforcement learning via human intervention
W Saunders, G Sastry, A Stuhlmueller, O Evans
arXiv preprint arXiv:1707.05173, 2017
Help or hinder: Bayesian models of social goal inference
T Ullman, C Baker, O Macindoe, O Evans, N Goodman, J Tenenbaum
Advances in neural information processing systems 22, 2009
Teaching models to express their uncertainty in words
S Lin, J Hilton, O Evans
arXiv preprint arXiv:2205.14334, 2022
Learning the Preferences of Ignorant, Inconsistent Agents
O Evans, A Stuhlmüller, ND Goodman
Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI-2016), 2016
The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"
L Berglund, M Tong, M Kaufmann, M Balesni, AC Stickland, T Korbak, ...
arXiv preprint arXiv:2309.12288, 2023
Agent-Agnostic Human-in-the-Loop Reinforcement Learning
D Abel, J Salvatier, A Stuhlmüller, O Evans
arXiv:1701.0407, 2017
Truthful AI: Developing and governing AI that does not lie
O Evans, O Cotton-Barratt, L Finnveden, A Bales, A Balwit, P Wills, ...
arXiv preprint arXiv:2110.06674, 2021
AI progress measurement
P Eckersley, Y Nasser, Y Bayle, O Evans, G Gebhart, D Schwenk
Electronic Frontier Foundation, 2017
Constructing and adjusting estimates for household transmission of SARS-CoV-2 from prior studies, widespread-testing and contact-tracing data
M Curmei, A Ilyas, O Evans, J Steinhardt
International Journal of Epidemiology 50 (5), 1444-1457, 2021
Active Reinforcement Learning: Observing Rewards at a Cost
D Krueger, J Leike, O Evans, J Salvatier
NIPS 2016 Workshop, 2016
Learning the Preferences of Bounded Agents
O Evans, A Stuhlmüller, ND Goodman
Advances in Neural Information Processing Systems (Bounded Optimality Workshop), 2015
Modeling Agents with Probabilistic Programs
O Evans, A Stuhlmüller, J Salvatier, D Filan, 2017
Taken out of context: On measuring situational awareness in LLMs
L Berglund, AC Stickland, M Balesni, M Kaufmann, M Tong, T Korbak, ...
arXiv preprint arXiv:2309.00667, 2023
Learning structured preferences
O Evans, L Bergen, JB Tenenbaum
Proceedings of the 32nd annual conference of the cognitive science society, 2010
How to catch an ai liar: Lie detection in black-box llms by asking unrelated questions
L Pacchiardi, AJ Chan, S Mindermann, I Moscovitz, AY Pan, Y Gal, ...
arXiv preprint arXiv:2309.15840, 2023
Modelling the Health and Economic Impacts of Population-Wide Testing, Contact Tracing and Isolation (PTTI) Strategies for COVID-19 in the UK
T Colbourn, W Waites, J Panovska-Griffiths, D Manheim, S Sturniolo, ...
SSRN, 2020
The system can't perform the operation now. Try again later.
Articles 1–20