Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations

TL;DR

This paper introduces RExC, a self-rationalizing model that grounds its predictions in background knowledge, achieving state-of-the-art performance while providing both extractive and natural language explanations.

Contribution

RExC is the first framework to simultaneously achieve SOTA task performance and generate two types of explanations grounded in background knowledge.

Findings

RExC outperforms previous models in task accuracy.

RExC produces higher quality explanations than prior methods.

Explanations in RExC are highly associated with predictions, indicating faithfulness.

Abstract

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.