The reviewed record of science sign in
Pith

arxiv: 2404.12014 · v1 · pith:UQPHNXU5 · submitted 2024-04-18 · cs.CL · cs.CR

Enhance Robustness of Language Models Against Variation Attack through Graph Integration

Reviewed by Pithpith:UQPHNXU5open to challenge →

classification cs.CL cs.CR
keywords languagemodelsvariationchangechinesegraphplmsattacks
0
0 comments X
read the original abstract

The widespread use of pre-trained language models (PLMs) in natural language processing (NLP) has greatly improved performance outcomes. However, these models' vulnerability to adversarial attacks (e.g., camouflaged hints from drug dealers), particularly in the Chinese language with its rich character diversity/variation and complex structures, hatches vital apprehension. In this study, we propose a novel method, CHinese vAriatioN Graph Enhancement (CHANGE), to increase the robustness of PLMs against character variation attacks in Chinese content. CHANGE presents a novel approach for incorporating a Chinese character variation graph into the PLMs. Through designing different supplementary tasks utilizing the graph structure, CHANGE essentially enhances PLMs' interpretation of adversarially manipulated text. Experiments conducted in a multitude of NLP tasks show that CHANGE outperforms current language models in combating against adversarial attacks and serves as a valuable contribution to robust language model research. These findings contribute to the groundwork on robust language models and highlight the substantial potential of graph-guided pre-training strategies for real-world applications.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.