The increasing use of complex and opaque black box models requires the adoption of interpretable measures, one such option is extractive rationalizing models, which serve as a more interpretable alternative. These models, also known as Explain-Then-Predict models, employ an explainer model to extract rationales and subsequently condition the predictor with the extracted information. Their primary objective is to provide precise and faithful explanations, represented by the extracted rationales. In this paper, we take a semi-supervised approach to optimize for the plausibility of extracted rationales. We adopt a pre-trained natural language inference (NLI) model and further fine-tune it on a small set of supervised rationales ($10\%$). The NLI predictor is leveraged as a source of supervisory signals to the explainer via entailment alignment. We show that, by enforcing the alignment agreement between the explanation and answer in a question-answering task, the performance can be improved without access to ground truth labels. We evaluate our approach on the ERASER dataset and show that our approach achieves comparable results with supervised extractive models and outperforms unsupervised approaches by $> 100\%$.

翻译：随着复杂且不透明的黑箱模型日益普及，采用可解释性措施变得至关重要，其中抽取式解释模型作为一种更具可解释性的替代方案应运而生。这些模型（也称为"先解释后预测"模型）通过一个解释器模型提取解释依据，并基于提取的信息对预测器进行条件化处理。其主要目标是提供由提取的解释依据所表征的精确且忠实的解释。本文采用半监督方法优化所提取解释依据的可信度。我们利用预训练的自然语言推理（NLI）模型，并在少量有监督解释依据（$10\%$）上对其进行微调。通过蕴含对齐，将NLI预测器作为监督信号的来源提供给解释器。结果表明，在问答任务中通过强制解释与答案之间的对齐一致性，可在无需真实标签的情况下提升性能。我们在ERASER数据集上评估了该方法，表明该方法达到了与有监督抽取式模型相当的性能，并将无监督方法的性能提升超过$100\%$。