一作ACL 2026Findings· Findings of ACL
S tance A ttack: Adversarial Attack for Stance Detection
Chenye Zhao · Cornelia Caragea
摘要
Stance detection aims to ascertain whether an author’s text is in favor, against, or neutral toward specific targets like public policies or social issues. While pretrained language models (PLMs) have greatly enhanced stance detection, they remain vulnerable to adversarial attacks—manipulations t...