U-M Generative AI Use Cases

Staff at Michigan Medicine receive thousands of faxes every day, with contents ranging from outpatient referrals to patient records and test results to prescriptions. Low quality scans and handwritten documents can be…

The Shared Services Center processes approximately 300,000 invoices annually, extracting key information from vendor-submitted vouchers. Previously, this process relied on a template-based system implemented in 2019, which was…

Using generally-available tools such as ChatGPT to write, debug, or modify Wolfram Language code can produce inferior results because these tools are not specifically trained to use Wolfram Language. Other Mathematica AI…

Assistant Professor Barbara Ericson aimed to improve the learning experience for students tackling close-ended write-code problems. Traditional methods often struggle to provide personalized, real-time feedback that aligns with students…

A graduate student from Mich Med Bioinformatics aimed to enhance the training process of deep reinforcement learning agents by generating reward signals through sentence evaluation. The challenge was to efficiently leverage a large-…

Efficiently curating metadata with controlled terminology is a critical yet time-consuming task in social science data management. Data depositors often provide insufficient metadata, necessitating extensive enhancement by data…

In large courses with multiple graders, maintaining consistent grading quality and limiting scoring variance can be challenging. Professor Peter Bodary aimed to address these issues by developing a system that assists human graders in…