講題：Leveraging Natural Language Processing in Large Language Models for Academic Advancement and Bias Mitigation

講者： 加州大學爾灣分校 電機工程與計算機學系 Quoc-Viet Dang助理教授

時間：2023.10.17 (二) 14:00-16:00

地點：人工智慧研究中心（管理大樓11樓）

線上直播：https://reurl.cc/V4z4ON

講者介紹：

Quoc-Viet "QV" Dang received his Ph.D. in Computer Systems and Software from the University of California, Irvine, United States in 2017. His dissertation research focused on using latent semantic analysis to create an intelligent recommendation system for students throughout their courses. Dr. Dang joined UC Irvine as an Assistant Professor of Teaching in 2017 where his primary focus is improving the educational experience of students throughout their college career. He continues his work in automated recommendation tools with research collaborators in the machine learning field and is facilitating multiple proof-of-concept student projects collaborating with industry partners including Texas Instruments, Thales, and Cadence.

演講大綱：

In recent years, large language models like ChatGPT have revolutionized the academic landscape, offering unprecedented opportunities for innovation in both teaching and research. This talk will delve into the novel applications and use-cases of these powerful language models, shedding light on their transformative potential in academia. The first part of the talk will explore how large language models have disrupted traditional academic curriculums. From augmenting course materials to assisting students with their assignments, these models are increasingly becoming indispensable tools for educators. We will highlight how we have used ChatGPT and similar models at the University of California, Irvine to create interactive and dynamic learning experiences, fostering student engagement and enhancing comprehension across various subjects. The second part of the talk will shift the focus towards current and future projects aimed at leveraging large language models and machine learning to identify and mitigate bias in academic courses. As educational institutions strive for inclusivity and diversity, it becomes imperative to address bias in course materials and interactions. We will discuss ongoing initiatives that employ minimally supervised natural language processing techniques to detect and rectify bias in course content, assessment tools, and student interactions. These projects are not only shaping a more equitable learning environment but also providing valuable insights into the dynamics of bias in education. Educators will now have the ability to process and synthesize vast amounts of student data to better support their individual needs. In conclusion, this talk will showcase the dual role of large language models in academia - as innovative tools that can enhance teaching and research, and as catalysts for addressing bias and fostering inclusivity in education. Attendees will gain a deeper understanding of the exciting possibilities and challenges associated with the integration of these models into academic practices, as well as insights into ongoing efforts to create a more equitable and supportive educational ecosystem.

主辦單位：智慧運算學院、人工智慧研究中心

※本活動無需報名。