让人类直接控制AI行为，发现掌控感提升使用体验和协作效果。
Controllable Complementarity: Subjective Preferences in Human-AI Collaboration
- 用行为塑造算法实现人类对AI行为的显式控制
- 有控制权时，用户觉得AI更有效、更愉快
- 适合关注人机协作体验与主观感受的研究者
人类-人工智能协作研究通常侧重客观性能，但理解人类主观偏好对于提升人机互补性和用户体验至关重要。本文通过行为塑造（Behavior Shaping, BS）算法，在共享工作空间任务中探究人类对可控性的偏好。实验一验证了当控制隐藏时，BS生成的AI策略在有效性上优于自对弈策略；实验二开放人类控制，结果显示参与者在能直接指挥AI行为时，认为其更高效且更具愉悦感。研究强调应同时关注任务表现与人类主观偏好，表明通过匹配人类偏好来设计AI，可使人机互补超越客观结果，融入主观体验维度。
原文摘要 · Abstract (English)
Research on human-AI collaboration often prioritizes objective performance. However, understanding human subjective preferences is essential to improving human-AI complementarity and human experiences. We investigate human preferences for controllability in a shared workspace task with AI partners using Behavior Shaping (BS), a reinforcement learning algorithm that allows humans explicit control over AI behavior. In one experiment, we validate the robustness of BS in producing effective AI policies relative to self-play policies, when controls are hidden. In another experiment, we enable human control, showing that participants perceive AI partners as more effective and enjoyable when they can directly dictate AI behavior. Our findings highlight the need to design AI that prioritizes both task performance and subjective human preferences. By aligning AI behavior with human preferences, we demonstrate how human-AI complementarity can extend beyond objective outcomes to include subjective preferences.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。