most citedTraining a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

391 citations · 583 across the 5 of their papers we have counts for

collaborators

5 papers

cs.HC202235 cited

Measuring Progress on Scalable Oversight for Large Language Models

Samuel R. Bowman, Jeeyoon Hyun, Ethan Perez +43

Developing safe and useful general-purpose AI systems will require us to make progress on scalable oversight: the problem of supervising systems that potentially outperform us on m…

cs.LG202287 cited

In-context Learning and Induction Heads

Catherine Olsson, Nelson Elhage, Neel Nanda +23

"Induction heads" are attention heads that implement a simple algorithm to complete token sequences like [A][B] ... [A] -> [B]. In this work, we present preliminary and indirect ev…

cs.LG202248 cited

Toy Models of Superposition

Nelson Elhage, Tristan Hume, Catherine Olsson +13

Neural networks often pack many unrelated concepts into a single neuron - a puzzling phenomenon known as 'polysemanticity' which makes interpretability much more challenging. This…

cs.LG202222 cited

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…

cs.CL2022391 cited

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…