Circuits extracted from inflectionally varied Polish sentences are more robust to adversarial word attacks than circuits from syncretic or English variants, identifying layer-0 attention heads as inflection-specific.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Unpacking Robustness in Inflectional Languages: Adversarial Evaluation and Mechanistic Insights
Circuits extracted from inflectionally varied Polish sentences are more robust to adversarial word attacks than circuits from syncretic or English variants, identifying layer-0 attention heads as inflection-specific.