Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations
This addresses the need for explainable AI by providing faithful, high-quality explanations without sacrificing performance, though it is incremental in combining existing explanation types with knowledge grounding.
The paper tackles the problem of models generating extractive rationales or natural language explanations (NLEs) for predictions often lagging behind state-of-the-art task performance, and introduces RExC, a self-rationalizing framework that grounds predictions and both explanation types in background knowledge, achieving SOTA task performance and significantly improving explanation quality.
Models that generate extractive rationales (i.e., subsets of features) or natural language explanations (NLEs) for their predictions are important for explainable AI. While an extractive rationale provides a quick view of the features most responsible for a prediction, an NLE allows for a comprehensive description of the decision-making process behind a prediction. However, current models that generate the best extractive rationales or NLEs often fall behind the state-of-the-art (SOTA) in terms of task performance. In this work, we bridge this gap by introducing RExC, a self-rationalizing framework that grounds its predictions and two complementary types of explanations (NLEs and extractive rationales) in background knowledge. Our framework improves over previous methods by: (i) reaching SOTA task performance while also providing explanations, (ii) providing two types of explanations, while existing models usually provide only one type, and (iii) beating by a large margin the previous SOTA in terms of quality of both types of explanations. Furthermore, a perturbation analysis in RExC shows a high degree of association between explanations and predictions, a necessary property of faithful explanations.