By explaining how humans would solve a given task, human rationales can provide strong learning signal for neural language models (LMs). Explanation regularization (ER) aims to improve LM generalization by pushing the LM's machine rationales (Which input tokens did the LM focus on?) to align with human rationales (Which input tokens would humans focus on?). Though prior works primarily study ER via in-distribution (ID) evaluation, out-of-distribution (OOD) generalization is often more critical in real-world scenarios, yet ER's effect on OOD generalization has been underexplored. In this paper, we introduce ER-Test, a framework for evaluating ER models' OOD generalization along three dimensions: unseen dataset tests, contrast set tests, and functional tests. Using ER-Test, we extensively analyze how ER models' OOD generalization varies with different ER design choices. Across two tasks and six datasets, ER-Test shows that ER has little impact on ID performance but can yield large OOD performance gains. Also, we find that ER can improve OOD performance even with limited rationale supervision. ER-Test's results help demonstrate ER's utility and establish best practices for using ER effectively.

翻译：通过解释人类如何解决给定任务，人类理据可为神经语言模型提供强大的学习信号。解释正则化旨在通过推动语言模型的机器理据（语言模型关注了哪些输入词元？）与人类理据（人类会关注哪些输入词元？）对齐，从而提升语言模型的泛化能力。尽管先前研究主要通过分布内评估来研究解释正则化，但在现实场景中，分布外泛化往往更为关键，然而解释正则化对分布外泛化的影响尚未得到充分探索。本文提出ER-Test框架，用于从三个维度评估解释正则化模型的分布外泛化能力：未见数据集测试、对比集测试和功能测试。利用ER-Test，我们深入分析了不同解释正则化设计选择如何影响模型的分布外泛化。在两个任务和六个数据集上的实验表明，解释正则化对分布内性能影响甚微，但能显著提升分布外性能。此外，我们发现即便在有限的理据监督条件下，解释正则化也能改善分布外性能。ER-Test的结果有助于证明解释正则化的效用，并确立有效使用解释正则化的最佳实践。