arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1907.12652cs.CYcs.AIcs.LG
收藏

模型准确性和解释保真度如何影响用户信任

How model accuracy and explanation fidelity influence user trust

GESIS - Leibniz Institute of the Social Sciences(GESIS——莱布尼茨社会科学研究所);University of Twente(特文特大学)

Andrea Papenmeier, Gwenn Englebienne, Christin Seifert

摘要:

机器学习系统已经在诸如营销、金融或数据采掘的领域中变得流行。虽然它们非常准确,但复杂的机器学习系统给工程师和用户带来了挑战。它们固有的复杂性使得不可能容易地判断它们的公平性以及变量和类之间统计学关系的正确性。可解释的人工智能旨在通过对解释和分类器进行建模来解决这一挑战,从而可能提高用户的信任度和接受度。然而,用户不应该被有说服力的,但不真实的解释所愚弄。因此,我们进行了一项用户研究,我们调查模型的准确性和解释保真度的影响,即如何真实的解释代表的基础模型,对用户的信任。我们的研究结果表明,准确性比可解释性更重要的用户信任。为分类结果添加解释可能会损害信任,例如添加无意义的解释时。我们还发现,用户不会被高保真的解释欺骗,从而信任一个糟糕的分类器。此外,我们发现观察(隐式)和自我报告(显式)的信任之间的不匹配。

英文摘要:

Machine learning systems have become popular in fields such as marketing, financing, or data mining. While they are highly accurate, complex machine learning systems pose challenges for engineers and users. Their inherent complexity makes it impossible to easily judge their fairness and the correctness of statistically learned relations between variables and classes. Explainable AI aims to solve this challenge by modelling explanations alongside with the classifiers, potentially improving user trust and acceptance. However, users should not be fooled by persuasive, yet untruthful explanations. We therefore conduct a user study in which we investigate the effects of model accuracy and explanation fidelity, i.e. how truthfully the explanation represents the underlying model, on user trust. Our findings show that accuracy is more important for user trust than explainability. Adding an explanation for a classification result can potentially harm trust, e.g. when adding nonsensical explanations. We also found that users cannot be tricked by high-fidelity explanations into having trust for a bad classifier. Furthermore, we found a mismatch between observed (implicit) and self-reported (explicit) trust.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑