703 citations · 3.4k across the 19 of their papers we have counts for
19 papers
Scaling Laws and Interpretability of Learning from Repeated Data
Danny Hernandez, Tom Brown, Tom Conerly +15
Recent large language models have been trained on vast datasets, but also often on repeated data, either intentionally for the purpose of upweighting higher quality data, or uninte…
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Yuntao Bai, Andy Jones, Kamal Ndousse +28
We apply preference modeling and reinforcement learning from human feedback (RLHF) to finetune language models to act as helpful and harmless assistants. We find this alignment tra…
Extremal bootstrapping: go with the flow
Sheer El-Showk, Miguel F. Paulos
The extremal functional method determines approximate solutions to the constraints of crossing symmetry, which saturate bounds on the space of unitary CFTs. We show that such solut…
Bootstrapping SCFTs with Four Supercharges
Nikolay Bobev, Sheer El-Showk, Dalimil Mazac +1
We study the constraints imposed by superconformal symmetry, crossing symmetry, and unitarity for theories with four supercharges in spacetime dimension . We show ho…
Bootstrapping the Three-Dimensional Supersymmetric Ising Model
Nikolay Bobev, Sheer El-Showk, Dalimil Mazac +1
We implement the conformal bootstrap program for three-dimensional CFTs with supersymmetry and find universal constraints on the spectrum of operator dimensions in…
Solving the 3d Ising Model with the Conformal Bootstrap II. c-Minimization and Precise Critical Exponents
Sheer El-Showk, Miguel F. Paulos, David Poland +3
We use the conformal bootstrap to perform a precision study of the operator spectrum of the critical 3d Ising model. We conjecture that the 3d Ising spectrum minimizes the central…