让外行也能通过操作配置黑箱AI，实现目标
Actionable AI: Enabling Non Experts to Understand and Configure AI Systems
- 通过直接操控设计可行动AI，降低使用门槛
- 22组非专家在不确定条件下达成良好表现
- 适合希望自主控制AI的普通用户和开发者
人与AI系统的交互引发了一个关键问题：人们如何理解这些系统？现有方法依赖可解释性、用户领域知识或稳定协作环境。当这些条件缺失时，本文提出设计可行动AI（Actionable AI），使非专家能够配置黑箱代理。我们以一个AI驱动的倒立摆游戏为实验场景，观察了22对参与者通过直接操作来配置系统。结果表明，在不确定条件下，非专家仍能取得良好性能；通过影响代理行为，他们展现出对系统的操作性理解，足以达成目标。基于此，我们提炼出可行动AI的设计启示。最终，我们主张将可行动AI作为开放访问基于AI代理的途径，赋予终端用户自主调节代理以实现自身目标的能力。
原文摘要 · Abstract (English)
Interaction between humans and AI systems raises the question of how people understand AI systems. This has been addressed with explainable AI, the interpretability arising from users' domain expertise, or collaborating with AI in a stable environment. In the absence of these elements, we discuss designing Actionable AI, which allows non-experts to configure black-box agents. In this paper, we experiment with an AI-powered cartpole game and observe 22 pairs of participants to configure it via direct manipulation. Our findings suggest that, in uncertain conditions, non-experts were able to achieve good levels of performance. By influencing the behaviour of the agent, they exhibited an operational understanding of it, which proved sufficient to reach their goals. Based on this, we derive implications for designing Actionable AI systems. In conclusion, we propose Actionable AI as a way to open access to AI-based agents, giving end users the agency to influence such agents towards their own goals.
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。