Adversarial robustness, domain generalization and dataset biases are three active lines of research contributing to out-of-distribution (OOD) evaluation on neural NLP models. However, a comprehensive, integrated discussion of the three research lines is still lacking in the literature. In this survey, we 1) compare the three lines of research under a unifying definition; 2) summarize the data-generating processes and evaluation protocols for each line of research; and 3) emphasize the challenges and opportunities for future work.

翻译：对抗鲁棒性、领域泛化与数据集偏差是当前神经网络NLP模型分布外评估领域的三个活跃研究方向。然而,文献中仍缺少对这三大研究方向的综合性系统论述。本综述旨在：1) 在统一框架下比较这三个研究方向;2) 总结每个研究方向的数据生成过程与评估协议;3) 强调未来工作面临的挑战与机遇。