AI, Take the Wheel: What Drives Delegation and Trust in Human-Computer Cooperative Question Answering?

2026-05-27

AI Summary

This study addresses the inefficiencies in human-AI collaborative question answering caused by suboptimal reliance—either over- or under-dependence on AI. Through a competitive question-answering experiment, it simultaneously examines two distinct forms of reliance: delegating answers autonomously to AI and accepting AI suggestions. Employing a paired human-AI design, behavioral data analysis, model confidence calibration, and cognitive bias identification, the research demonstrates that overconfidence and confirmation bias significantly impair collaboration quality. Findings reveal that participants missed 3.9% of correct AI suggestions and were misled by incorrect ones 1.7% of the time; notably, when both human and AI initially provided the same incorrect answer, 64.5% of participants still underestimated AI’s capability. Overall, effective human-AI collaboration substantially outperformed either agent acting alone.

Abstract

AI systems are fallible, and humans can make mistakes in deciding whether to trust AI over their own judgment. Thus, improving human-AI collaboration requires understanding when, why, and how humans decide to rely on AI. We study two distinct reliance decisions: the delegation choice -- deciding when to let AI act autonomously without knowing its output, and the adoption choice -- evaluating AI suggestions and deciding how to use them. Both of these decoupled reliance patterns shape collaboration, but prior work rarely studies them together in realistic settings with the same users. We address this gap by studying collaborative human--AI teams competing in a question-answering game in which humans can choose when and how to work with AI agents to win. Our 24 matches pair 23 expert humans with 16 AI agents, capturing 387 delegation and 1440 adoption decisions. While human--AI collaboration performs better than either AI or humans alone, humans make suboptimal collaboration decisions, both under-relying on correct AI suggestions (3.9% of opportunities missed) and over-relying when AI misleads them (1.7%). Both parties contribute wrong answers: reported model confidence is near chance when humans and AI disagree, while confirmation bias drives higher under-reliance (64.5%) when an AI suggestion agrees with humans' initial incorrect answer. To close this gap, we recommend calibrated confidence, evidence-grounded explanations, and mechanisms that help users refine trust.

Problem

• human-AI collaboration
• delegation
• adoption
• trust
• reliance decisions

Innovation

• delegation choice
• adoption choice
• human-AI collaboration
• calibrated confidence
• evidence-grounded explanations