1 code implementation • 1 Feb 2024 • Alex J. Chan, Hao Sun, Samuel Holt, Mihaela van der Schaar
Reinforcement Learning from Human Feedback (RLHF) has been credited as the key advance that has allowed Large Language Models (LLMs) to effectively follow instructions and produce useful assistance.
no code implementations • 5 Dec 2023 • Alex J. Chan, José Luis Redondo García, Fabrizio Silvestri, Colm O'Donnel, Konstantina Palla
We train large language models on extensive datasets of media news and articles to create culturally attuned models.
no code implementations • 23 Nov 2023 • Hao Sun, Alex J. Chan, Nabeel Seedat, Alihan Hüyük, Mihaela van der Schaar
On the one hand, it brings opportunities for safe policy improvement under high-stakes scenarios like clinical guidelines.
no code implementations • 13 Nov 2023 • Alex J. Chan, Alihan Huyuk, Mihaela van der Schaar
Machine learning models are being increasingly deployed to take, or assist in taking, complicated and high-impact decisions, from quasi-autonomous vehicles to clinical decision support systems.
1 code implementation • 26 Sep 2023 • Lorenzo Pacchiardi, Alex J. Chan, Sören Mindermann, Ilan Moscovitz, Alexa Y. Pan, Yarin Gal, Owain Evans, Jan Brauner
Large language models (LLMs) can "lie", which we define as outputting false statements despite "knowing" the truth in a demonstrable sense.
no code implementations • 11 Nov 2022 • Tennison Liu, Alex J. Chan, Boris van Breugel, Mihaela van der Schaar
It is important to guarantee that machine learning algorithms deployed in the real world do not result in unfairness or unintended social consequences.
2 code implementations • 11 Oct 2022 • Alex J. Chan, Mihaela van der Schaar
Consider making a prediction over new test data without any opportunity to learn from a training set of labelled data - instead given access to a set of expert models and their predictions alongside some limited information about the dataset used to train them.
no code implementations • ICLR 2022 • Alizée Pace, Alex J. Chan, Mihaela van der Schaar
Building models of human decision-making from observed behaviour is critical to better understand, diagnose and support real-world policies such as clinical care.
2 code implementations • ICLR 2022 • Alex J. Chan, Alicia Curth, Mihaela van der Schaar
Human decision making is well known to be imperfect and the ability to analyse such processes individually is crucial when attempting to aid or improve a decision-maker's ability to perform a task, e. g. to alert them to potential biases or oversights on their part.
1 code implementation • 8 Jun 2021 • Alex J. Chan, Ioana Bica, Alihan Huyuk, Daniel Jarrett, Mihaela van der Schaar
Understanding decision-making in clinical environments is of paramount importance if we are to bring the strengths of machine learning to ultimately improve patient outcomes.
2 code implementations • 12 Feb 2021 • Alex J. Chan, Mihaela van der Schaar
Bayesian inference over the reward presents an ideal solution to the ill-posed nature of the inverse reinforcement learning problem.
no code implementations • ICML 2020 • Alex J. Chan, Ahmed M. Alaa, Zhaozhi Qian, Mihaela van der Schaar
In this paper, we develop an approximate Bayesian inference scheme based on posterior regularisation, wherein unlabelled target data are used as "pseudo-labels" of model confidence that are used to regularise the model's loss on labelled source data.