Skip to main content

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

Caoyun Fan (Shanghai Jiao Tong University); Wenqing Chen (Sun Yat-sen University); Jidong Tian (Shanghai Jiao Tong University); Yitian Li (Shanghai Jiao Tong University); Hao He (Shanghai Jiao Tong University); Yaohui Jin (Shanghai Jiao Tong University)

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
07 Jun 2023

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.

More Like This

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00