Year: 2023
Type: preprint
Abstract: Large-scale language models achieved state-of-the-art performance over a number of language tasks. However, they fail on adversarial language examples, which are sentences optimized to fool the language models but with similar semantic meanings for humans. While prior work focuses on making the language model robust at training time, retraining for robustness is often unrealistic for large-scale foundation models. Instead, we propose to make the language models robust at test time. By dynamically adapting the input sentence with predictions from masked words, we show that we can reverse many language adversarial attacks. Since our approach does not require any training, it works for novel tasks at test time and can adapt to novel adversarial corruptions. Visualizations and empirical results on two popular sentence classification datasets demonstrate that our method can repair adversarial language attacks over 65% o
Source: arXiv (Cornell University)
Authors: McDermott, Noah Thomas, Yang, Junfeng, Mao, Chengzhi
Institution: Columbia University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4388093257