学术报告：Towards Responsible Large Language Models
报告人：吴方照 博士，微软亚洲研究院
时间：2024/3/24 [周日] 上午 9:30-11:30
地点：电子工程馆9-208
题目: Towards Responsible Large Language Models
摘要: Large Language Models (LLMs) have shown powerful capability in many different tasks and been widely used in many real-world applications. It is crucial to make sure that LLMs to run in a responsible way so that their positive impact on society can be maximized and their negative impact can be minimized. In this talk, I will introduce the safety risks brought by LLMs and the research efforts to alleviate them.
报告人简介: Fangzhao Wu graduated from the Department of Electronics Engineering at Tsinghua University, and is now a researcher at Social Computing group, Microsoft Research Asia. His research mainly focuses on responsible AI, especially LLM safety, privacy, copyright, and social impact.