Building Trust with a Teachable Artificial Intelligence: The Case of Repeated Trust Games
收藏资源简介：
This study explores the teaching of Artificial Intelligence (AI) systems in a repeated trust game. We evaluate whether participants trust the AI and teach it to adopt the most beneficial strategies among a set of four options with different levels of benefit. Results indicate that participants are initially cautious with the AI but increase their trust throughout the experiment, especially those with initially low trust. Participants imperfectly teach the AI, initially adopting beneficial strategies, then progressively learning the most advantageous ones while discarding those that offer minimal or no benefit. We also observe that participants inefficiently choose to avoid positive learning when it involves a risk of large losses. In additional tasks, we observe that participants naturally seek ways to exploit the AI, although a significant portion maintains human fairness in the interaction. Moreover, they effectively transfer prior knowledge to similar tasks. We conclude that participants trust an AI they can teach to generate significant benefits, although the risk of loss limits this trust and the efficiency of teaching.
本研究围绕重复信任博弈场景下的人工智能（Artificial Intelligence）系统教学展开探究。本研究旨在评估参与者是否会信任该AI，并能否教会其在四种不同收益层级的可选策略集合中选取最优收益策略。实验结果表明，参与者最初对AI抱有谨慎态度，但在实验全程中逐步提升对其信任度，其中初始信任水平较低的参与者这一变化尤为显著。参与者对AI的教学并不完善：他们初期会采用有益的策略，随后逐步掌握最优收益策略，并摒弃那些收益微薄或无收益的选项。此外，研究还发现，当面临大额损失风险时，参与者会低效地选择规避正向学习。在附加任务中，我们观察到参与者会本能地寻求利用AI的途径，但仍有相当比例的参与者在交互过程中秉持人类公平性准则。同时，参与者能够有效地将先前习得的知识迁移至同类任务中。综上，参与者会信任那些可通过教学实现显著收益的AI，但损失风险会限制这种信任以及教学的效率。
