Bias problems in large language models and how to mitigate them

• المؤلف الرئيسي: Ong, Adrian Zhi Ying
• مؤلفون آخرون: Luu Anh Tuan
• التنسيق: Final Year Project
• اللغة: English
• منشور في: Nanyang Technological University 2024
• الموضوعات: Computer and Information Science; Bias; Large language model
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/181163
• المؤسسة: Nanyang Technological University

Pretrained Language Models (PLMs) like ChatGPT have become integral to various industries, revolutionising applications from customer service to software development. However, these PLMs are often trained on vast, unmoderated datasets, which may contain social biases that can be propagated in the m...