Research Internships at Microsoft provide a dynamic environment for research careers with a network of world-class research labs led by globally-recognized scientists and engineers, who pursue innovation in a range of scientific and technical disciplines to help solve complex challenges in diverse fields, including computing, healthcare, economics, and the environment.

Processing documents, by querying, generating or acting on their content, is one of the most common applications of large language models (LLMs). Although LLMs enable a quantum leap in document processing, they are error prone. We will explore how to augment the statistical processing that LLMs provide with formal (or "logical") reasoning to reduce the error rate.