Rationales behind answers not only explain model decisions but boost language models to reason well on complex reasoning tasks. However, obtaining impeccable rationales is often impossible. Besides, it is non-trivial to estimate the degree to which the rationales are faithful enough to encourage model performance. Thus, such reasoning tasks often compel models to output correct answers under undesirable rationales and are sub-optimal compared to what the models are fully capable of. In this work, we propose how to deal with imperfect rationales causing aleatoric uncertainty. We first define the ambiguous rationales with entropy scores of given rationales, using model prior beliefs as informativeness. We then guide models to select one of two different reasoning models according to the ambiguity of rationales. We empirically argue that our proposed method produces robust performance superiority against the adversarial quality of rationales and low-resource settings.

翻译：答案背后的理由不仅能够解释模型决策，还能提升语言模型在复杂推理任务中的推理能力。然而，获取完美无瑕的理由往往是不可能的。此外，评估理由在多大程度上足够可信以促进模型性能也并非易事。因此，这种推理任务常常迫使模型在不理想的理由下输出正确答案，相较于模型完全可达到的性能而言是次优的。在这项工作中，我们提出了如何处理导致偶然不确定性的不完美理由。我们首先利用模型先验信念作为信息量，通过给定理由的熵分数来定义模棱两可的理由。接着，我们引导模型根据理由的模糊性，从两种不同的推理模型中选择一种。通过实证研究，我们论证了所提出的方法在面对对抗性理由质量及低资源设置时，能够产生稳健的性能优势。