Moshira A. Ebrahim

SCAR-FND: Auditing Lexical Shortcuts in the ISOT Fake News Benchmark Through Automatic Discovery and Matched Ablation

Very high scores on fake-news benchmarks can be misleading when artifacts introduced during dataset construction are strongly tied to the class labels. This study presents SCAR-FND, a source-confound-aware auditing framework that identifies label-associated lexical shortcuts from training data and then measures how str...