Disambiguating the meaning of pejorative words can help improve the detection of misogynistic language in Italian tweets.
Large language models offer significant advantages over state-of-the-art models for hate speech detection, even without fine-tuning. Fine-tuning can further improve performance, but the effects depend on the specific model and dataset characteristics.
Adversarial datasets, collected by exploiting model weaknesses, can improve the robustness of hate speech detection models.