Mitigating Demographic Disparities in Explanation-Human Alignment via Rationale Regularization
We study explanation fairness in hate speech detection. High classification performance does not always mean that a model produces equally plausible explanations for different demographic groups. Using the HateXplain dataset, we introduce Plausibility-EFG, a metric that measures the largest difference in explanation plausibility across demographic groups by comparing model-generated token attributions with human-annotated rationales. We evaluate BERT, RoBERTa, and ADV-RoBERTa, an adversarially trained model, using Integrated Gradients and SHAP. Our results show that ADV-RoBERTa improves classification performance and alignment between explanations and human rationales while reducing expla...
| Authors | Suryansh Talukdar, Taha Sarwat, Jonathan Rusert |
|---|---|
| Primary category | cs.CL |
| Published | 15 October 2026 |
| Last updated at source | 15 October 2026 |
Popularity, last 6 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 24 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.