@article{softhatebenchevaluatingmoderationmodelsa, title = {SoftHateBench: Evaluating Moderation Models Against Reasoning-Driven, Policy-Compliant Hostility}, author = {Xuanyu Su and Diana Inkpen and Nathalie Japkowicz}, year = {2026}, eprint = {2601.20256}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.20256}, }