Improving the Out-Of-Distribution Generalization Capability of Language Models: Counterfactually-Augmented Data is not Enough

arxiv(2023)

引用 0|浏览31
暂无评分
摘要
Counterfactually-Augmented Data (CAD) has the potential to improve language models' Out-Of-Distribution (OOD) generalization capability, as CAD induces language models to exploit causal features and exclude spurious correlations. However, the empirical results of OOD generalization on CAD are not as efficient as expected. In this paper, we attribute the inefficiency to Myopia Phenomenon caused by CAD: language models only focus on causal features that are edited in the augmentation and exclude other non-edited causal features. As a result, the potential of CAD is not fully exploited. Based on the structural properties of CAD, we design two additional constraints to help language models extract more complete causal features contained in CAD, thus improving the OOD generalization capability. We evaluate our method on two tasks: Sentiment Analysis and Natural Language Inference, and the experimental results demonstrate that our method could unlock CAD's potential and improve language models' OOD generalization capability.
更多
查看译文
关键词
Counterfactually-Augmented Data,Out-Of-Distribution Generalization,Language Models
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要