396 citations · 494 across the 9 of their papers we have counts for
9 papers
Formalizing the presumption of independence
Paul Christiano, Eric Neyman, Mark Xu
Mathematical proof aims to deliver confident conclusions, but a very similar process of deduction can be used to make uncertain estimates that are open to revision. A key ingredien…
Learning to summarize from human feedback
Nisan Stiennon, Long Ouyang, Jeff Wu +6
As language models become more powerful, training and evaluation are increasingly bottlenecked by the data and metrics used for a particular task. For example, summarization models…
Fine-Tuning Language Models from Human Preferences
Daniel M. Ziegler, Nisan Stiennon, Jeffrey Wu +5
Reward learning enables the application of reinforcement learning (RL) to tasks where reward is defined by human judgment, building a model of reward by asking humans questions. Mo…
A Cryptographic Test of Quantumness and Certifiable Randomness from a Single Quantum Device
Zvika Brakerski, Paul Christiano, Urmila Mahadev +2
We consider a new model for the testing of untrusted quantum devices, consisting of a single polynomial-time bounded quantum device interacting with a classical polynomial-time ver…
Collaborative prediction with expert advice
Paul Christiano
Many practical learning systems aggregate data across many users, while learning theory traditionally considers a single learner who trusts all of their observations. A case in poi…
Provably Manipulation-Resistant Reputation Systems
Paul Christiano
We consider a community of users who must make periodic decisions about whether to interact with one another. We propose a protocol which allows honest users to reliably interact w…