Seminars and Events
The Duality of Bias in Large Language Models: Leveraging Community Perspectives and Uncovering Ideological Vulnerabilities
Event Details
Speaker: Zihao He, USC/ISI
Conference Room Location: ISI-MDR CR#689
Meeting hosts only admit on-line guests that they know to the Zoom meeting. Hence, you’re highly encouraged to use your USC account to sign into Zoom.
If you’re an outside visitor, please inform us at (nlg-seminar-host(at)isi.edu) to make us aware of your attendance so we can admit you. Specify if you will attend remotely or in person at least one business day prior to the event. Provide your: full name, job title and professional affiliation and arrive at least 10 minutes before the seminar begins.
If you do not have access to the 6th Floor for in-person attendance, please check in at the 10th floor main reception desk to register as a visitor and someone will escort you to the conference room location.
Join Zoom Meeting
https://usc.zoom.us/j/98068942358?pwd=MYU6jzrZIjaIYPEuIHG0C61g3BTEXB.1
Meeting ID: 980 6894 2358
Passcode: 716186
Large language models (LLMs) have demonstrated remarkable capabilities in understanding and generating human-like text. As these models become increasingly integrated into various applications, it is crucial to understand their potential for both beneficial and problematic impacts on society. In this talk, I will explore the dual nature of bias in LLMs through two recent studies that employ similar methodologies but reveal contrasting implications. First, I will discuss COMMUNITY-CROSS-INSTRUCT, an innovative framework that aligns LLMs with online community perspectives to create “digital twins” for efficient public opinion analysis. Then, I will present findings on LLMs’ susceptibility to ideological influences through targeted instruction tuning.
By examining these complementary perspectives, I aim to showcase the innovative potential of LLMs in social science research while also highlighting the importance of understanding their malleability. This presentation will contribute to the ongoing dialogue on responsible AI development, illustrating how careful application of LLM capabilities can lead to valuable insights while also emphasizing the need for awareness of their limitations and vulnerabilities.
Speaker Bio
Zihao He is a final-year PhD candidate in computer science at University of Southern California (USC). He is advised by Prof. Kristina Lerman. His research interests lie at the intersection of natural language processing and computational social science. Specifically, Zihao has been focusing on evaluating the societal impacts of large language models (LLMs) and investigating their vulnerability to ideological influences. His work has been published in top-tier conferences like ACL, EMNLP, and ICWSM.
Previously, Zihao received his undergraduate degree from Beijing University of Posts and Telecommunications (BUPT). He spent one year of master’s studies at Tsinghua University. He has interned at TikTok, Amazon, and DiDi Global.
If speaker approves to be recorded for this NL Seminar talk, it will be posted on the USC/ISI YouTube page within 1-2 business days: https://www.youtube.com/user/USCISI.
Subscribe here to learn more about upcoming seminars: https://www.isi.edu/events/
For more information on the NL Seminar series and upcoming talks, please visit: