arXiv:2506.21613v3 Announce Type: replace Abstract: Mental health industry faces growing concerns regarding hate speech directed at children's on social media, as exposure to such content can contribute to adverse psychological outcomes during critical stages of development. Current hate speech datasets and detection systems provide limited support for child-focused applications because they are primarily designed for adults and lack dedicated representations of age-specific characteristics associated with hate speech directed at children's. To address this gap, we introduce ChildGuard, a larg
Source: arXiv cs.CL — read the full report at the original publisher.