243 citations · 663 across the 15 of their papers we have counts for
14 papers · 1 filter
Solving math word problems with process- and outcome-based feedback
Jonathan Uesato, Nate Kushman, Ramana Kumar +6
Recent work has shown that asking language models to generate reasoning steps improves performance on many reasoning tasks. When moving beyond prompting, this raises the question o…
Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals
Rohin Shah, Vikrant Varma, Ramana Kumar +4
The field of AI alignment is concerned with AI systems that pursue unintended goals. One commonly studied mechanism by which an unintended goal might arise is specification gaming,…
Improving alignment of dialogue agents via targeted human judgements
Amelia Glaese, Nat McAleese, Maja Trębacz +31
We present Sparrow, an information-seeking dialogue agent trained to be more helpful, correct, and harmless compared to prompted language model baselines. We use reinforcement lear…
An Empirical Investigation of Learning from Biased Toxicity Labels
Neel Nanda, Jonathan Uesato, Sven Gowal
Collecting annotations from human raters often results in a trade-off between the quantity of labels one wishes to gather and the quality of these labels. As such, it is often only…
Avoiding Tampering Incentives in Deep RL via Decoupled Approval
Jonathan Uesato, Ramana Kumar, Victoria Krakovna +3
How can we design agents that pursue a given objective when all feedback mechanisms are influenceable by the agent? Standard RL algorithms assume a secure reward function, and can…
REALab: An Embedded Perspective on Tampering
Ramana Kumar, Jonathan Uesato, Richard Ngo +3
This paper describes REALab, a platform for embedded agency research in reinforcement learning (RL). REALab is designed to model the structure of tampering problems that may arise…