About this document

Pap 1 by abdullahalarafat147 is a document available to read on EtoBox.

This study benchmarks large language models (LLMs) like GPT-4 and GPT-3.5 for hate speech detection in Assamese, a low-resource language, using zero-shot and few-shot learning methods. The results indicate that GPT-4 significantly outperforms previous models, achieving a macro-F1 score of 0.870, while also addressing challenges related to code-mixing and cultural nuances. The research contributes to the development of scalable hate speech moderation systems in underrepresented languages by providing a compr

Author

abdullahalarafat147

Language

EN