Human-AI Complementarity: A Goal for Amplified Oversight

2025-10-30

AI Summary

This study addresses the challenging human supervision task of verifying the factual accuracy of AI-generated outputs. Methodologically, we propose a human-AI collaborative fact-checking framework featuring an AI confidence estimation and explanation generation module; it dynamically integrates AI scores with human judgments while modulating human trust by presenting only verifiable search evidence—not definitive conclusions. Our key contribution is the first systematic empirical validation that “lightweight AI assistance”—defined as providing only auditable evidence—significantly mitigates human overreliance on AI. Results demonstrate that our fusion mechanism improves human verification accuracy by 12.7% over both pure-human and pure-AI baselines. These findings establish a scalable technical pathway and cognitively grounded design principles for building trustworthy AI supervision paradigms.

Technology Category

• Humans and AI: Other Foundations of Human Computation & AI
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

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.

Problem

• Improving human oversight quality using AI assistance systems
• Enhancing fact-verification accuracy through human-AI complementary ratings
• Optimizing AI assistance types to prevent human over-reliance

Innovation

• AI ratings combined with human ratings
• AI assistant improves human verification accuracy
• Evidence display fosters appropriate human trust