SOURCE-LINKED INTELLIGENCE

From Specialization to Generalization: Instruction-tuned LLMs for Robust Harmful Content Mitigation

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Large language models (LLMs) demonstrate impressive performance across a wide range of general NLP tasks; however, their effectiveness in sensitive domains, such as hate speech detection, remains less clear. Prior studies comparing prompted LLMs with state-of-the-art encoder-based models (e.g., BERT variants (Roy et al., 2023; Dönmez et al., 2024)) have shown only marginal gains, suggesting that LLMs may not excel in hate speech detection or mitigation. In this work, we revisit this question through the lens of instruction tuning. By thoroughly unifying 36 English hate speech datasets spanning

Read original source ↗ Open in workspace

recordType

paper

region

Global