人们高估了生成式AI与人类决策的契合度，实验发现预测偏差显著。
Human Misperception of Generative-AI Alignment: A Laboratory Experiment
- 通过经济决策实验，对比人与AI在风险、时间偏好等场景下的选择
- 人对AI的选择预测值比实际更接近自身选择，平均偏差达显著水平
- 个体预测高度依赖自身行为，提示认知偏差影响对AI的信任
我们开展了一项激励型实验室实验，研究人们在经济决策情境中对生成式人工智能（GenAI）对齐程度的感知。采用涵盖风险、时间偏好、社会偏好和策略互动等多个领域的经济问题面板，要求受试者为自己做决策，并预测GenAI代表人类用户会如何选择。结果发现，人们普遍高估了GenAI与人类选择的一致性：在所有问题中，受试者对GenAI选择的平均预测值显著更接近平均人类选择，而非GenAI真实选择。在个体层面，同一问题中不同受试者对GenAI选择的预测与其自身选择高度相关。我们进一步通过一个简单的理论模型探讨了这种过度对齐感知的潜在影响。
原文摘要 · Abstract (English)
We conduct an incentivized laboratory experiment to study people's perception of generative artificial intelligence (GenAI) alignment in the context of economic decision-making. Using a panel of economic problems spanning the domains of risk, time preference, social preference, and strategic interactions, we ask human subjects to make choices for themselves and to predict the choices made by GenAI on behalf of a human user. We find that people overestimate the degree of alignment between GenAI and human choices. In every problem, human subjects' average prediction about GenAI's choice is substantially closer to the average human-subject choice than it is to the GenAI choice. At the individual level, different subjects' predictions about GenAI's choice in a given problem are highly correlated with their own choices in the same problem. We explore the implications of people overestimating GenAI alignment in a simple theoretical model.
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。