Investigating the Effect of Natural Language Explanations on Out-of-Distribution Generalization in Few-shot NLI
This addresses the problem of poor generalization in neural models for NLP researchers, but it is incremental as it builds on existing datasets and methods without achieving gains.
The study investigated whether natural language explanations improve out-of-distribution generalization in few-shot natural language inference, but found that generated explanations did not enhance prediction performance despite competitive BLEU scores.
Although neural models have shown strong performance in datasets such as SNLI, they lack the ability to generalize out-of-distribution (OOD). In this work, we formulate a few-shot learning setup and examine the effects of natural language explanations on OOD generalization. We leverage the templates in the HANS dataset and construct templated natural language explanations for each template. Although generated explanations show competitive BLEU scores against groundtruth explanations, they fail to improve prediction performance. We further show that generated explanations often hallucinate information and miss key elements that indicate the label.