NOV 13, 2025 3:20 PM PST

GenAI Falls Short in Decision Analysis Without Human Input

How effective is generative AI (GenAI) at brainstorming independently? This is what a recent study published in Decision Analysis hopes to address as an international team of researchers investigated the potential for GenAI to perform tasks independently without the need for human involvement. This study has the potential to help scientists, engineers, and the public better understand GenAI applications and how their capabilities can be enhanced.

For the study, the researchers examined how ChatGPT performed independently on a series of tasks and prompts with the goal of ascertaining its ability to independently brainstorm. This study comes as ChatGPT continues to become engrained in everyday lives, from investing to cooking to travel, and much more. In the end, the researchers found that while ChatGPT successfully completed individual tasks, larger tasks often required human expert input. Additionally, the team emphasized the importance of including human input for decision making.

“Generative AI performs well on several criteria,” said Dr. Jay Simon, who is an Associate Professor of Information Technology & Analytics at American University and lead author of the study. “But it still struggles with producing coherent and nonredundant sets of objectives. Human decision analysts are essential to refine and validate what the AI produces.”

Along with the applications noted above, GenAI is often used for creating new text, images, audio, video, business processes, marketing, computer programming, data analysis, art, and much more. Despite these applications, this study demonstrates how GenAI still has a long way to go for performing in-depth tasks independently without the need of human input. Additionally, this also demonstrates the importance of human-machine interaction, meaning that GenAI might always need human input and might never be able to perform specific tasks independently.

What new insight into GenAI will researchers make in the coming years and decades? Only time will tell, and this is why we science!

As always, keep doing science & keep looking up!

Sources: Decision Analysis, EurekAlert!

About the Author
Master's (MA/MS/Other)
Laurence Tognetti is a six-year USAF Veteran who earned both a BSc and MSc from the School of Earth and Space Exploration at Arizona State University. Laurence is extremely passionate about outer space and science communication, and is the author of "Outer Solar System Moons: Your Personal 3D Journey".
You May Also Like
Loading Comments...