Publications (6)
Measuring Faithfulness in Chain-of-Thought Reasoning
Tamera Lanham, Anna Chen, Ansh Radhakrishnan +27
Large language models (LLMs) perform better when they produce step-by-step, "Chain-of-Thought" (CoT) reasoning before answering a question, but it is unclear if the stated reasonin…
Discovering Language Model Behaviors with Model-Written Evaluations
Ethan Perez, Sam Ringer, KamilÄ LukoÅ¡iÅ«tÄ +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…
The Capacity for Moral Self-Correction in Large Language Models
Deep Ganguli, Amanda Askell, Nicholas Schiefer +46
We test the hypothesis that language models trained with reinforcement learning from human feedback (RLHF) have the capability to "morally self-correct" -- to avoid producing harmf…
Studying Large Language Model Generalization with Influence Functions
Roger Grosse, Juhan Bae, Cem Anil +14
When trying to gain better visibility into a machine learning model in order to understand and mitigate the associated risks, a potentially valuable source of evidence is: which tr…
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…
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…