Abstract:  As advances in natural language processing (NLP) and large language models (LLMs) continue, there is growing interest in applying them to real-world problems. In this talk, I will present my lab’s dual focus: developing innovative NLP technologies to address critical healthcare challenges and tackling fundamental NLP issues. The first part will highlight our work on developing and evaluating LLM-based methods for diagnosis prediction and supporting physicians in the diagnostic decision-making process, as well as a study on the deployment of LLM technology in a real-world hospital, showcasing AI’s potential in healthcare. The second part will explore foundational NLP challenges that have the potential for broader impact across various domains, such as efficient training for complex reasoning in LLMs and improving their interpretability.

Bio: Dr. Yanjun Gao is an Assistant Professor in the Department of Biomedical Informatics at the University of Colorado, Anschutz Medical Campus.  She leads the Language, Reasoning, and Knowledge (LARK) Lab, where they develop and evaluate natural language processing (NLP) methods, particularly large language models (LLMs), to analyze medical data with the goal of building safe and reliable AI systems for healthcare and beyond. Dr. Gao earned her PhD in Computer Science and Engineering from the NLP Lab at Pennsylvania State University and was previously a postdoctoral researcher at the University of Wisconsin-Madison. She actively publishes on major NLP conferences and medical informatics journals, and is the recipient of the National Institutes of Health K99/R00 award.

Please join us in ECCR 265 or on Zoom: https://cuboulder.zoom.us/j/91008309605