Measure and Improve Robustness in NLP Models: A Survey

TL;DR

This survey comprehensively reviews how robustness in NLP models is defined, measured, and improved, unifying diverse research efforts and proposing systematic mitigation strategies for safer deployment.

Contribution

It provides a unifying framework for understanding robustness in NLP, connecting various definitions, evaluation methods, and mitigation strategies in a systematic manner.

Findings

Unified multiple definitions of robustness in NLP.

Reviewed diverse evaluation and mitigation strategies.

Outlined open challenges and future research directions.

Abstract

As NLP models achieved state-of-the-art performances over benchmarks and gained wide applications, it has been increasingly important to ensure the safe deployment of these models in the real world, e.g., making sure the models are robust against unseen or challenging scenarios. Despite robustness being an increasingly studied topic, it has been separately explored in applications like vision and NLP, with various definitions, evaluation and mitigation strategies in multiple lines of research. In this paper, we aim to provide a unifying survey of how to define, measure and improve robustness in NLP. We first connect multiple definitions of robustness, then unify various lines of work on identifying robustness failures and evaluating models' robustness. Correspondingly, we present mitigation strategies that are data-driven, model-driven, and inductive-prior-based, with a more systematic view of how to effectively improve robustness in NLP models. Finally, we conclude by outlining open challenges and future directions to motivate further research in this area.