“信任垃圾”导致对高度歧视性预测模型的不合理支持
"Trust Junk" Leads to Unjustified Support for Highly Discriminatory Predictive Models
浏览论文内容
中文总结 AI 辅助
研究发现在可解释人工智能中，模型解释里提供的准确但多余或无关的数据会使人们对明显歧视性和不公平的模型产生不合理信任，提示XAI设计者和开发者要注意工作中的修辞及可视化带来的潜在问题。
中文摘要 AI 辅助
数据可视化的说服力可能会出错：例如，在可解释人工智能（XAI）环境中，可视化会导致对预测模型的过度信任。本文通过众包研究表明，在模型解释中提供准确（但多余或无关）的数据，实际上会导致对模型产生不合理的信任和其他积极信念，即使该模型明显具有歧视性和不公平性。研究结果表明，XAI设计者和开发者需要考虑其工作中隐含或明确的修辞，并警惕可视化可能赋予模型不应有的信任。
英文摘要
The persuasive power of data visualizations can go awry: for instance, in an explainable AI (XAI) context, visualizations can produce over-trust of predictive models. In this paper, we use a crowdsourced study to show that providing accurate (but superfluous or irrelevant) data in a model explanation can, in fact, result in unjustified trust and other positive beliefs about a model, even when the model is patently discriminatory and unfair. Our results suggest that XAI designers and developers need to consider the implicit or explicit rhetorics of their work, and beware of the potential of visualizations to imbue models with unearned trust.
发表机构
- Northeastern University（东北大学）
机构由 AI 辅助整理，请以论文原文为准。
