AI has become increasingly embedded in technological resources, and many people opt to use LLMs as a tool for everyday tasks. Efficiency, ease of use, UI/UX design, etc., all contribute to user preference. Presenting data for each preference metric to users may change their perception of the model and, subsequently, their choice of model.
This project focuses on a survey and interview model. First, participants fill out a survey regarding their values and opinions towards AI. They then complete five tasks using a different LLM model for each task and provide feedback on each model’s performance and usability. Statistics about the LLMs are presented to the user while using each model. Multiple metrics, including effectiveness, ease of use, and user satisfaction, are recorded about each model. The participants then rank the models and are interviewed about their experience using the LLMs.
Researchers combine quantitative analysis and reflexive thematic analysis to investigate what influences AI model choice. This research contributes to the broader understanding of AI’s social reputation and influence.
Team
Faculty
- Dr. Sarah Morrison-Smith
- Dr. Han Dong
Undergraduate Researchers
- Madeline Brogen
- Royce Carol
- Gwen Sawicki