Explanation based Bias Decoupling Regularization for Natural Language Inference

arXiv:2404.13390v1 Announce Type: new
Abstract: The robustness of Transformer-based Natural Language Inference encoders is frequently compromised as they tend to rely more on dataset biases than on the intended task-relevant features. Recent studies have attempted to mitigate this by reducing the weight of biased samples during the training process. However, these debiasing methods primarily focus on identifying which samples are biased without explicitly determining the biased components within each case. This limitation restricts those methods' capability in out-of-distribution inference. To …

abstract arxiv bias biases cs.cl dataset features however inference language natural natural language process regularization robustness samples studies training transformer type