Measuring machine learning harms from stereotypes: requires understanding who is being harmed by which errors in what ways
CoRR(2024)
摘要
As machine learning applications proliferate, we need an understanding of
their potential for harm. However, current fairness metrics are rarely grounded
in human psychological experiences of harm. Drawing on the social psychology of
stereotypes, we use a case study of gender stereotypes in image search to
examine how people react to machine learning errors. First, we use survey
studies to show that not all machine learning errors reflect stereotypes nor
are equally harmful. Then, in experimental studies we randomly expose
participants to stereotype-reinforcing, -violating, and -neutral machine
learning errors. We find stereotype-reinforcing errors induce more
experientially (i.e., subjectively) harmful experiences, while having minimal
changes to cognitive beliefs, attitudes, or behaviors. This experiential harm
impacts women more than men. However, certain stereotype-violating errors are
more experientially harmful for men, potentially due to perceived threats to
masculinity. We conclude that harm cannot be the sole guide in fairness
mitigation, and propose a nuanced perspective depending on who is experiencing
what harm and why.
更多查看译文
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要