Probing Critical Learning Dynamics of PLMs for Hate Speech Detection
This provides empirical groundwork for improving hate speech detection using PLMs, though it appears incremental in analyzing existing methods.
The paper investigated how various aspects of pretrained language models (PLMs) affect their performance in hate speech detection, finding early performance peaks during pretraining, limited benefits from recent pretraining data, and specific layer significance during finetuning.
Despite the widespread adoption, there is a lack of research into how various critical aspects of pretrained language models (PLMs) affect their performance in hate speech detection. Through five research questions, our findings and recommendations lay the groundwork for empirically investigating different aspects of PLMs' use in hate speech detection. We deep dive into comparing different pretrained models, evaluating their seed robustness, finetuning settings, and the impact of pretraining data collection time. Our analysis reveals early peaks for downstream tasks during pretraining, the limited benefit of employing a more recent pretraining corpus, and the significance of specific layers during finetuning. We further call into question the use of domain-specific models and highlight the need for dynamic datasets for benchmarking hate speech detection.