Research seminar by professor Kevin ASHLEY

Department : Law and Tax

Speaker : Kevin ASHLEY (University of Pittsburgh)

Room S.118 

and by zoom : https://hec-fr.zoom.us/j/99522725859

“LLMs, GenAI, and Legal Argument Schemes”

Abstract

Argument schemes have long played an important role in knowledge-based computational models of case-based legal argument. Argument schemes are templates or “blueprints” for typical kinds of legal arguments such as arguing by analogizing to past cases or distinguishing a precedent. Case-based legal argument involves using past decided cases in arguments to persuade a judge how to decide a similar later case. Computational models of case-based legal argument frequently employ factors, stereotypical patterns of fact that strengthen or weaken a side’s argument with respect to a type of legal claim. “Knowledge-based” computational models of legal argument explicitly represent aspects of legal knowledge such as legal rules, concepts, and factors. 

Today, knowledge-based models are passé, having been replaced by machine learning, large language models, and generative AI. Argument schemes, however, may still have a role to play. Argument schemes employing factors can inform argument-scheme-based prompts to lead large language models to generate case-based legal arguments. Supportive prompting can enable generative AI to identify case factors and factor magnitudes with which to implement argument schemes. 

In this talk, I will provide a brief account of the changes in AI computational models of case-based legal reasoning in the last eight years and focus on a series of projects in my lab at the University of Pittsburgh in which my students have developed argument-scheme-based prompting.