Can Rationalization Improve Robustness?

Howard Chen, Jacqueline He, Karthik Narasimhan, Danqi Chen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

17 Scopus citations

Abstract

A growing line of work has investigated the development of neural NLP models that can produce rationales-subsets of input that can explain their model predictions. In this paper, we ask whether such rationale models can provide robustness to adversarial attacks in addition to their interpretable nature. Since these models need to first generate rationales (“rationalizer”) before making predictions (“predictor”), they have the potential to ignore noise or adversarially added text by simply masking it out of the generated rationale. To this end, we systematically generate various types of 'AddText' attacks for both token and sentence-level rationalization tasks and perform an extensive empirical evaluation of state-of-the-art rationale models across five different tasks. Our experiments reveal that rationale models show promise in improving robustness but struggle in certain scenarios-e.g., when the rationalizer is sensitive to position bias or lexical choices of the attack text. Further, leveraging human rationales as supervision does not always translate to better performance. Our study is a first step towards exploring the interplay between interpretability and robustness in the rationalize-then-predict framework.

Original languageEnglish (US)
Title of host publicationNAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics
Subtitle of host publicationHuman Language Technologies, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages3792-3805
Number of pages14
ISBN (Electronic)9781955917711
StatePublished - 2022
Event2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022 - Seattle, United States
Duration: Jul 10 2022Jul 15 2022

Publication series

NameNAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference

Conference

Conference2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022
Country/TerritoryUnited States
CitySeattle
Period7/10/227/15/22

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Hardware and Architecture
  • Information Systems
  • Software

Fingerprint

Dive into the research topics of 'Can Rationalization Improve Robustness?'. Together they form a unique fingerprint.

Cite this