无关数据误导用户信任有偏模型，揭示XAI设计隐含风险
"Trust Junk" Leads to Unjustified Support for Highly Discriminatory Predictive Models
- 用冗余数据增强解释，反而提升用户对有偏模型的信任
- 即使模型明显歧视，用户仍因可视化产生过度信赖
- 警示XAI设计者警惕视觉呈现带来的虚假可信度
数据可视化具有强大的说服力：在可解释人工智能（XAI）场景中，可视化可能导致用户对预测模型产生过度信任。本文通过众包实验发现，在模型解释中加入准确但多余或无关的数据，即便模型存在明显歧视与不公，仍会引发用户不合理的信任及其他正面评价。结果表明，XAI设计者与开发者需关注其工作中的隐含或显性修辞，警惕可视化赋予模型的未经证实的信任。
原文摘要 · Abstract (English)
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.
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。