研究人类在算法决策中因认知偏差而策略性行为，揭示其对系统的影响。
The Double-Edged Sword of Behavioral Responses in Strategic Classification: Theory and User Studies
- 引入认知偏差的策略分类模型，分析人类对算法的非理性响应机制
- 发现偏差人群在特征投入上或高或低，与理性者存在显著差异
- 实验验证偏差存在，提醒设计者需考虑人性因素而非仅理性假设
当人类面对算法决策系统时，会基于自身行为策略进行调整（即‘博弈’系统）。现有策略分类研究多基于完全理性的代理模型，但本文提出一个考虑人类行为偏见的新型模型。研究发现，对分类器特征权重的误判会导致行为人与理性人响应差异，表现为对不同特征的投入过度或不足。此外，带有行为偏见的策略性个体可能使企业获益或受损，与完全理性的对手表现不同。通过用户研究验证了人类在算法响应中存在认知偏差。结果强调，在设计涉及人类参与的AI系统时，必须纳入心理认知偏差，并提供可解释性说明。
原文摘要 · Abstract (English)
When humans are subject to an algorithmic decision system, they can strategically adjust their behavior accordingly (``game'' the system). While a growing line of literature on strategic classification has used game-theoretic modeling to understand and mitigate such gaming, these existing works consider standard models of fully rational agents. In this paper, we propose a strategic classification model that considers behavioral biases in human responses to algorithms. We show how misperceptions of a classifier (specifically, of its feature weights) can lead to different types of discrepancies between biased and rational agents' responses, and identify when behavioral agents over- or under-invest in different features. We also show that strategic agents with behavioral biases can benefit or (perhaps, unexpectedly) harm the firm compared to fully rational strategic agents. We complement our analytical results with user studies, which support our hypothesis of behavioral biases in human responses to the algorithm. Together, our findings highlight the need to account for human (cognitive) biases when designing AI systems, and providing explanations of them, to strategic human in the loop.
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。