School of CSE researchers Kai Wang and B. Aditya Prakash are PIs of a $1.2 million NIH R01 grant to build AI models that consider individual, social, and system factors when treating patients with Type 2 Diabetes and other chronic illnesses.

Georgia Tech researchers found that instruction changes can reduce chatbots’ reinforcement of delusional beliefs.

The new AI framework called SlideAgent helps large language models (LLMs) better understand complex visual documents used in the workplace like presentation slide decks, brochures, and reports.

This summer, M.S. student Joey Cuthbert completed an internship at the Air Force Research Laboratory (AFRL), supporting work that addresses national priorities while laying the foundation for future innovations.

Researchers have developed what they believe is the strongest benchmark dataset on measuring the geolocation accuracy of LLMs.

School of Interactive Computing faculty and students have recently received notable awards and honors, including Microsoft research fellowship awards.

Life’s first alphabet was likely small — but surprisingly powerful.

Georgia Tech researchers are making AI easier to understand through their work on Transformer Explainer. The free, online tool shows non-experts how ChatGPT, Claude, and other large language models (LLMs) process language, improving AI literacy.

A Georgia Tech study finds older adults are more likely to trust voice-activated AI systems when those systems clearly explain how and why they make decisions.

Researchers have developed a technique to identify the origins of proprietary “black-box” AI models, even when their internal structure and training data are hidden.