KNOW How to Make Up Your Mind! Adversarially Detecting and Alleviating Inconsistencies in Natural Language Explanations

The 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023) While recent works have been considerably improving the quality of the natural language explanations (NLEs) generated by a model to justify its predictions, there is very limited research in detecting and alleviating...

Full description

Saved in:
Bibliographic Details
Main Authors Jang, Myeongjun, Majumder, Bodhisattwa Prasad, McAuley, Julian, Lukasiewicz, Thomas, Camburu, Oana-Maria
Format Journal Article
LanguageEnglish
Published 05.06.2023
Subjects
Computer Science - Artificial Intelligence
Computer Science - Computation and Language
Online AccessGet full text

Cover

More Information
Summary:The 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023) While recent works have been considerably improving the quality of the natural language explanations (NLEs) generated by a model to justify its predictions, there is very limited research in detecting and alleviating inconsistencies among generated NLEs. In this work, we leverage external knowledge bases to significantly improve on an existing adversarial attack for detecting inconsistent NLEs. We apply our attack to high-performing NLE models and show that models with higher NLE quality do not necessarily generate fewer inconsistencies. Moreover, we propose an off-the-shelf mitigation method to alleviate inconsistencies by grounding the model into external background knowledge. Our method decreases the inconsistencies of previous high-performing NLE models as detected by our attack.
DOI:10.48550/arxiv.2306.02980