LLMs and Finetuning: Benchmarking cross-domain performance for hate speech detection

arXiv:2310.18964v2 Announce Type: replace
Abstract: In the evolving landscape of online communication, hate speech detection remains a formidable challenge, further compounded by the diversity of digital platforms. This study investigates the effectiveness and adaptability of pre-trained and fine-tuned Large Language Models (LLMs) in identifying hate speech, to address two central questions: (1) To what extent does the model performance depend on the fine-tuning and training parameters?, (2) To what extent do models generalize to cross-domain hate speech detection? and (3) …

abstract adaptability arxiv benchmarking challenge communication cs.cl detection digital diversity domain finetuning hate speech hate speech detection landscape language language models large language large language models llms performance platforms speech study type