Tag: AI evaluation

Duke will lead a nearly $25 million national initiative to evaluate, standardize and responsibly implement AI tools for older adults ...

A first-of-its-kind study asked ten multimodal AI models to rate their own mental workload on real dental examinations using a ...

A new 200,000-question benchmark from Carnegie Mellon University reveals that leading vision-language models perform at random chance when interpreting engineering ...

A scoping review of 69 studies finds that large language models can boost efficiency in cross-cultural project teams but often ...

Researchers propose small qualitative evaluations, a human-in-the-loop framework tested on extreme heat advice, showing that human agreement on rubric dimensions ...