New study shows LLMs respond differently based on user’s motivation

Chaewon Bak
Michelle Bak
Jessie Chin
Jessie Chin, Assistant Professor

A new study conducted by PhD student Michelle Bak and Assistant Professor Jessie Chin, which was recently published in the Journal of the American Medical Informatics Association (JAMIA), reveals how large language models (LLMs) respond to different motivational states. In their evaluation of three LLM-based generative conversational agents (GAs)—ChatGPT, Google Bard, and Llama 2—the researchers found that while GAs are able to identify users' motivation states and provide relevant information when individuals have established goals, they are less likely to provide guidance when the users are hesitant or ambivalent about changing their behavior.

Bak provides the example of an individual with diabetes who is resistant to changing their sedentary lifestyle.  

"If they were advised by a doctor that exercising would be necessary to manage their diabetes, it would be important to provide information through GAs that helps them increase an awareness about healthy behaviors, become emotionally engaged with the changes, and realize how their unhealthy habits might affect people around them. This kind of information can help them take the next steps toward making positive changes," said Bak.

Current GAs lack specific information about these processes, which puts the individual at a health disadvantage. Conversely, for individuals who are committed to changing their physical activity levels (e.g., have joined personal fitness training to manage chronic depression), GAs are able to provide relevant information and support. 

"This major gap of LLMs in responding to certain states of motivation suggests future directions of LLMs research for health promotion," said Chin.

Bak's research goal is to develop a digital health solution based on using natural language processing and psychological theories to promote preventive health behaviors. She earned her bachelor's degree in sociology from the University of California Los Angeles.

Chin’s research aims to translate social and behavioral sciences theories to design technologies and interactive experiences to promote health communication and behavior across the lifespan. She leads the Adaptive Cognition and Interaction Design (ACTION) Lab at the University of Illinois. Chin holds a BS in psychology from National Taiwan University, an MS in human factors, and a PhD in educational psychology with a focus on cognitive science in teaching and learning from the University of Illinois.

Updated on
Backto the news archive

Related News

iSchool represented at Charleston Conference

iSchool adjunct and affiliate faculty will participate in virtual and in-person sessions of the 2024 Charleston Conference. The conference is an annual gathering that draws librarians, publishers, vendors, and others to discuss issues relating to the acquisition and publication of books and serials. 

Schneider group to present at ASIS&T workshop

Members of Associate Professor Jodi Schneider’s group will present their research at the Association for Information Science and Technology (ASIS&T) Workshop on Informetric, Scientometric, and Scientific and Technical Information Research, which will be held virtually on November 6 and 13. The MET-STI 2024 Workshop is collaboratively hosted by the Special Interest Group for Metrics (SIG-MET) and Special Interest Group for Scientific and Technical Information (SIG-STI) of ASIS&T.

Jodi Schneider

Wong co-edits new edition of Reference and Information Services

Adjunct Lecturer Melissa Wong (MSLIS '94) and Laura Saunders, professor of library and information science at Simmons University, are the co-editors of Reference and Information Services: An Introduction, Seventh Edition, which was recently published by Bloomsbury Libraries Unlimited. The textbook provides a comprehensive update to the previous edition, also co-edited by Wong and Saunders, and serves as an essential resource for LIS students and practitioners alike.

Melissa Wong

iSchool researchers to present at ASSETS 2024

iSchool faculty and students will present their research at the 26th International Association for Computing Machinery (ACM) Special Interest Group (SIG) ACCESS Conference on Computers and Accessibility (ASSETS 2024), which will be held on October 28-30 in St. John's, Newfoundland and Labrador, Canada. The conference is the premier forum for presenting research on design, evaluation, use, and education related to computing for people with disabilities and older adults.

iSchool well represented at ASIS&T 2024

iSchool faculty, staff, and students will participate in the 87th Annual Meeting of the Association for Information Science and Technology (ASIS&T), which will be held on October 25-29 in Calgary, Canada. The theme of this year's conference is "Putting People First: Responsibility, Reciprocity, and Care in Information Research and Practice." The meeting is the premier international conference dedicated to the study of information, people, and technology in contemporary society.

iSchool Building