Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations
Bodhisattwa Prasad Majumder Oana-Maria Camburu Thomas Lukasiewicz Julian McAuley
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 fa
中文速览
可解释AI领域长期面临一个两难困境：能给出解释的模型往往在任务准确率上落后于那些"黑箱"最优模型，而且现有方法通常只能提供一种解释形式——要么是从输入中抽取关键片段的"抽取式理由"（extractive rationale），要么是用自然语言描述推理过程的"自然语言解释"（natural language explanation，NLE），二者兼顾的方案几乎没有。为此，本文提出了RExC框架，其核心思路是让模型在做预测和生成解释时都"有据可查"：先从输入中抽出关键特征，再用这些特征去查询COMET等背景知识库，筛选出最相关的知识片段，据此生成NLE，最后再做出最终预测，全流程端到端训练。在自然语言和视觉语言五项任务上的实验表明，RExC不仅同时输出两种互补解释，还在解释质量上大幅超越此前最优方法，任务准确率也追平了不提供任何解释的最强黑箱模型，并通过扰动分析验证了解释与预测之间的高度关联性（即忠实性）。这项工作实质上消除了可解释性与性能之间的取舍代价，为构建既透明又准确的AI系统提供了一条可行路径。
原文 arXiv:2106.13876;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2106.13876v4