Picture for Yuntao Bai

Yuntao Bai

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Add code
Jan 17, 2024
Viaarxiv icon

Specific versus General Principles for Constitutional AI

Add code
Oct 20, 2023
Figure 1 for Specific versus General Principles for Constitutional AI
Figure 2 for Specific versus General Principles for Constitutional AI
Figure 3 for Specific versus General Principles for Constitutional AI
Figure 4 for Specific versus General Principles for Constitutional AI
Viaarxiv icon

The Capacity for Moral Self-Correction in Large Language Models

Add code
Feb 18, 2023
Figure 1 for The Capacity for Moral Self-Correction in Large Language Models
Figure 2 for The Capacity for Moral Self-Correction in Large Language Models
Figure 3 for The Capacity for Moral Self-Correction in Large Language Models
Figure 4 for The Capacity for Moral Self-Correction in Large Language Models
Viaarxiv icon

Discovering Language Model Behaviors with Model-Written Evaluations

Add code
Dec 19, 2022
Viaarxiv icon

Constitutional AI: Harmlessness from AI Feedback

Add code
Dec 15, 2022
Viaarxiv icon

Measuring Progress on Scalable Oversight for Large Language Models

Add code
Nov 11, 2022
Viaarxiv icon

In-context Learning and Induction Heads

Add code
Sep 24, 2022
Viaarxiv icon

Language Models (Mostly) Know What They Know

Add code
Jul 16, 2022
Figure 1 for Language Models (Mostly) Know What They Know
Figure 2 for Language Models (Mostly) Know What They Know
Figure 3 for Language Models (Mostly) Know What They Know
Figure 4 for Language Models (Mostly) Know What They Know
Viaarxiv icon

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

Add code
Jun 10, 2022
Viaarxiv icon

Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Add code
Apr 12, 2022
Figure 1 for Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Figure 2 for Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Figure 3 for Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Figure 4 for Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Viaarxiv icon