Student Speakers: Werner Hager and Morgan Gray

Speaker: Werner Hager
Title: Exploring Behavioral Diversity and Teamwork in Multi Human AI Teams

Abstract:
Teamwork consists of a variety of interconnected actions and behaviors between team members that continuously adapt to complete the objectives of the team as the team interacts. Understanding how these behaviors develop depending on the objective and individuals within a human team is essential to develop AI agents that can work well in a team with both other agents and humans. This project examines how teamwork can be evaluated and the development of appropriate metrics for assessing team dynamics. I will discuss differences in behavior between humans and agents, as well as how that behavior evolves for both individuals and teams as they continue to interact. These insights are used to inform the design of a diverse set of agents which can capture the varied range of behaviors exhibited by humans in team settings.

Bio:
Werner Hager is a PhD student in the Intelligent Systems Program at the University of Pittsburgh, advised by Dr. Michael Lewis. His research focuses on reinforcement learning and human-agent interaction. He received his undergraduate in Data Science from the Penn State College of Engineering.

Speaker: Morgan Gray
Title: Using LLMs to Discover Legal Factors

Abstract:
Factors are a foundational component of legal analysis and computational models of legal reasoning. These factor-based representations enable lawyers, judges, and AI and Law researchers to reason about legal cases. In this paper, we introduce a methodology that leverages large language models (LLMs) to discover lists of factors that effectively represent a legal domain. Our method takes as input raw court opinions and produces a set of factors and associated definitions. We demonstrate that a semi-automated approach, incorporating minimal human involvement, produces factor representations that can predict case outcomes with moderate success, if not yet as well as expert-defined factors can.

Bio:
Morgan Gray is a fourth year Ph.D. student in Intelligent Systems at the University of Pittsburgh. The primary areas of his scholarship are natural language processing, legal text analytics, machine learning, and criminal procedure. He received his B.A. from Thiel College in 2016, his J.D. from Duquesne Kline School of Law in 2019. He served as a judicial clerk for the Commonwealth Court of Pennsylvania for two years and is admitted to practice in Pennsylvania and the Western District of Pennsylvania. He also is an adjunct professor at the Thomas R. Kline School of Law of Duquesne University and has received the University’s Creative Teaching Award for his efforts. He is also a Faculty Scholar for the Carl. G. Grefenstette Center for Ethics in Science, Technology, and Law.