可解释性中的性别偏见：探究事后方法的性能差异
Gender Bias in Explainability: Investigating Performance Disparity in Post-hoc Methods
AI总结：
本文发现广泛使用的事后特征归因方法在三项任务和五个语言模型上表现出显著的性别差异，即使使用无偏见数据集训练依然存在，强调了在可解释性方法中解决解释公平性的重要性。
摘要：
尽管对解释方法的应用和评估研究不断扩展，但解释方法在跨子群性能差异方面的公平性仍是一个常被忽视的问题。本文通过在三项任务和五个语言模型上的研究填补了这一空白，结果表明广泛使用的事后特征归因方法在忠实度、鲁棒性和复杂性方面表现出显著的性别差异。即使模型在特别无偏见的数据集上进行预训练或微调，这些差异依然存在，这表明我们观察到的差异不仅仅是带有偏见的训练数据的后果。我们的结果强调了在开发和应用可解释性方法时解决解释中差异的重要性，因为这可能导致对某些子群的偏见结果，在高风险情境中具有尤为关键的启示。此外，我们的发现强调了必须将解释的公平性与整体模型公平性和可解释性一起，作为监管框架中的一项要求。
英文摘要：
While research on applications and evaluations of explanation methods continues to expand, fairness of the explanation methods concerning disparities in their performance across subgroups remains an often overlooked aspect. In this paper, we address this gap by showing that, across three tasks and five language models, widely used post-hoc feature attribution methods exhibit significant gender disparity with respect to their faithfulness, robustness, and complexity. These disparities persist even when the models are pre-trained or fine-tuned on particularly unbiased datasets, indicating that the disparities we observe are not merely consequences of biased training data. Our results highlight the importance of addressing disparities in explanations when developing and applying explainability methods, as these can lead to biased outcomes against certain subgroups, with particularly critical implications in high-stakes contexts. Furthermore, our findings underscore the importance of incorporating the fairness of explanations, alongside overall model fairness and explainability, as a requirement in regulatory frameworks.
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。
