Human-AI Complementarity: A Goal for Amplified Oversight
This addresses the problem of ensuring AI safety and alignment for users and developers, offering incremental improvements in human-AI collaboration for oversight tasks.
The paper tackles the challenge of verifying AI-generated facts by combining human and AI oversight, finding that AI-assisted human fact-checking improves accuracy, with search results and evidence fostering appropriate trust better than AI explanations and labels.
Human feedback is critical for aligning AI systems to human values. As AI capabilities improve and AI is used to tackle more challenging tasks, verifying quality and safety becomes increasingly challenging. This paper explores how we can leverage AI to improve the quality of human oversight. We focus on an important safety problem that is already challenging for humans: fact-verification of AI outputs. We find that combining AI ratings and human ratings based on AI rater confidence is better than relying on either alone. Giving humans an AI fact-verification assistant further improves their accuracy, but the type of assistance matters. Displaying AI explanation, confidence, and labels leads to over-reliance, but just showing search results and evidence fosters more appropriate trust. These results have implications for Amplified Oversight -- the challenge of combining humans and AI to supervise AI systems even as they surpass human expert performance.