Study Examines Annotator Disagreement in Multi-Dialect Arabic Sexism Detection
A new arXiv paper finds that sexism detection datasets for Arabic dialects typically collapse annotator judgments into a single majority label, obscuring disagreement and model errors.
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-11-19 05:00 · arXiv cs.CL
What Majority Labels Hide: Annotator Disagreement and Model Errors in Multi-Dialect Arabic Sexism Detection