New study examines gender bias in LLMs

Zhixuan Zhou
Kyrie Zhixuan Zhou
Madelyn Sanfilippo
Madelyn Rose Sanfilippo, Assistant Professor

A new study by PhD student Kyrie Zhixuan Zhou and Assistant Professor Madelyn Rose Sanfilippo has uncovered the existence of gender bias in Large Language Models (LLMs) in the U.S. and China. The researchers examined public discussion about this topic on the social media platforms Twitter (now X) and Weibo, finding reports of gender bias in the LLMs ChatGPT and Ernie, China's ChatGPT-equivalent.

Zhou and Sanfilippo were invited to summarize their findings in the Montreal AI Ethics Institute (MAIEI) article, "Public Perceptions of Gender Bias in Large Language Models: Cases of ChatGPT and Ernie." MAIEI is an international nonprofit research institute with a mission to democratize AI ethics literacy. The summary will also be featured in AI Ethics Brief, the institute's weekly newsletter for technical leaders and policymakers around the world.

According to Zhou, finding public discussion on gender bias in ChatGPT on Twitter was straightforward, with over 350 posts on the subject. However, posts about gender bias in Ernie were more difficult to uncover on Weibo, due to China's strict censorship on online discussions about feminism. Zhou and Sanfilippo found that "cultural factors impact biases in LLMs since they were trained on data that reflect those cultural contexts." They observed implicit gender bias in discussion about ChatGPT, e.g., associating different genders with different professional titles, but explicit gender bias in discussion about Ernie, e.g., devaluing women by their age.

"Gender bias is always a severe and under-investigated issue in information technology," said Zhou. "By understanding and proposing ways to solve gender bias in AI, we aim to create a more inclusive and fair tech infrastructure in the LLM era."

To rectify the situation, the researchers propose governance recommendations to regulate gender bias in LLMs as well as the development of educational tutorials to equip AI creators with awareness and knowledge of AI gender bias.

Zhou's research interests are in tech ethics and accessibility. He aims to understand, design, and govern ICT/AI experience for vulnerable populations such as older adults, people with disabilities, women in conservative cultures, and people in authoritarian regimes. Zhou earned his BEng in computer science from Wuhan University.

Sanfilippo uses mixed methods to address research questions about participation in and the legitimacy of sociotechnical governance; social justice issues associated with sociotechnical governance; privacy in sociotechnical systems; and differences between policies or regulations and sociotechnical practice. Her work practically supports decision-making in, management of, and participation in a diverse public sphere. She earned her MS and PhD in information science from Indiana University.

Updated on
Backto the news archive

Related News

Zhou defends dissertation

Doctoral candidate Kyrie Zhixuan Zhou successfully defended his dissertation, "A Pragmatic and Human-centered Approach to Promoting Software Accessibility: Design, Education, Governance," on April 3.

Zhixuan Zhou

Library Trends explores the philosophy of information in issue and webinar

The School of Information Sciences at the University of Illinois Urbana-Champaign is pleased to announce the publication of Library Trends 73 (1–2). Inspired by the contributions of Marcia Bates, this issue, "Design and the Philosophy of Information," highlights the cultural, social, and philosophical dimensions of information design. Ken Herold served as guest editor. 

Design and the Philosophy of Information

Knox appointed interim dean

Professor Emily Knox has been appointed to serve as interim dean of the School of Information Sciences, pending approval by the Board of Trustees. Until officially approved, her title will be interim dean designate. The appointment will begin April 1, 2025.

Emily Knox

iSchool instructors ranked as excellent

Fifty-six iSchool instructors were named in the University's List of Teachers Ranked as Excellent for Fall 2024 and Winter 2024-2025. The rankings are released every semester, and results are based on the ratings from the Instructor and Course Evaluation System (ICES) questionnaire forms maintained by Measurement and Evaluation in the Center for Innovation in Teaching and Learning. 

iSchool Building

Ocepek and Sanfilippo co-edit book on misinformation

Assistant Professor Melissa Ocepek and Assistant Professor Madelyn Rose Sanfilippo have co-edited a new book, Governing Misinformation in Everyday Knowledge Commons, which was recently published by Cambridge University Press. An open access edition of the book is available, thanks to support from the Governing Knowledge Commons Research Coordination Network (NSF 2017495). The new book explores the socio-technical realities of misinformation in a variety of online and offline everyday environments. 

Governing Misinformation in Everyday Knowledge Commons book