activity
20172026
most citedBeyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

565 citations · 2.1k across the 18 of their papers we have counts for

collaborators
Showing 2022Show all

9 papers · 1 filter

cs.CL2022★ 52 cited

Discovering Language Model Behaviors with Model-Written Evaluations

Ethan Perez, Sam Ringer, Kamilė Lukošiūtė +60

As language models (LMs) scale, they develop many novel behaviors, good and bad, exacerbating the need to evaluate how they behave. Prior work creates evaluations with crowdwork (w…

cs.CL2022★ 334 cited

Constitutional AI: Harmlessness from AI Feedback

Yuntao Bai, Saurav Kadavath, Sandipan Kundu +48

As AI systems become more capable, we would like to enlist their help to supervise other AIs. We experiment with methods for training a harmless AI assistant through self-improveme…

cs.HC2022★ 35 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.LG2022★ 87 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.CL2022★ 119 cited

Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Deep Ganguli, Liane Lovitt, Jackson Kernion +33

We describe our early efforts to red team language models in order to simultaneously discover, measure, and attempt to reduce their potentially harmful outputs. We make three main…

cs.CL2022★ 170 cited

Language Models (Mostly) Know What They Know

Saurav Kadavath, Tom Conerly, Amanda Askell +33

We study whether language models can evaluate the validity of their own claims and predict which questions they will be able to answer correctly. We first show that larger models a…