Speech and Rhetorical Studies Commons^™

The Unreasonable Effectiveness Of Large Language Models In Zero-Shot Semantic Annotation Of Legal Texts, Jaromir Savelka, Kevin D. Ashley

Articles

The emergence of ChatGPT has sensitized the general public, including the legal profession, to large language models' (LLMs) potential uses (e.g., document drafting, question answering, and summarization). Although recent studies have shown how well the technology performs in diverse semantic annotation tasks focused on legal texts, an influx of newer, more capable (GPT-4) or cost-effective (GPT-3.5-turbo) models requires another analysis. This paper addresses recent developments in the ability of LLMs to semantically annotate legal texts in zero-shot learning settings. Given the transition to mature generative AI systems, we examine the performance of GPT-4 and GPT-3.5-turbo(-16k), comparing it to the previous …

Reconceiving Argument Schemes As Descriptive And Practically Normative, Brian N. Larson, David Seth Morrison

Faculty Scholarship

We propose a revised definition of “argument scheme” that focuses on describing argumentative performances and normative assessments that occur within an argumentative context, the social context in which the scheme arises. Our premise-and-conclusion structure identifies the typical instantiation of an argument in the argumentative context, and our critical framework describes a set of normative assessments available to participants in the context, what we call practically normative assessments. We distinguish this practical normativity from the rationally or universally normative assessment that might be imposed from outside the argumentative context. Thus, the practical norms represented in an argument scheme may still be …

The Writing’S On The Wall: Using Multimedia Presentation Principles From The Museum World To Improve Law School Pedagogy, Cecilia A. Silver

Dickinson Law Review (2017-Present)

Law school pedagogy is a relic. Nearly 150 years after Christopher Langdell pioneered the case method, the typical doctrinal course remains predominantly a verbal domain, featuring lectures, Socratic dialogue, and final exams. But the visual disconnect between legal education and legal practice does students a disservice. Under the proliferating influence of laptops, iPads, smartphones, and Zoom, students now read, work, and study electronically more than they ever have before. So instead of business as usual, it’s time to embrace “visualization”—using multimedia to enhance, or even supplant, the near-exclusive reliance on language—to build a more vibrant and inclusive learning environment.

Law …

A Rhetorical Analysis Of Opening Statements In Trial: Reconsidering The Classical Canon Of Invention, Andrew Chandler

Undergraduate Theses

This analysis of 21 opening statements probes at current persuasive practices employed by trial attorneys through the lens of mainstream legal advice and an expanded definition of rhetorical invention – one which includes both discovery and creation. An evaluation of such practice reveals the utility, and furthermore the duty of the advocate, to draw upon an expanded realm of available arguments.

Automatically Extracting Meaning From Legal Texts: Opportunities And Challenges, Kevin D. Ashley

Articles

This paper examines impressive new applications of legal text analytics in automated contract review, litigation support, conceptual legal information retrieval, and legal question answering against the backdrop of some pressing technological constraints. First, artificial intelligence (Al) programs cannot read legal texts like lawyers can. Using statistical methods, Al can only extract some semantic information from legal texts. For example, it can use the extracted meanings to improve retrieval and ranking, but it cannot yet extract legal rules in logical form from statutory texts. Second, machine learning (ML) may yield answers, but it cannot explain its answers to legal questions or …

Using Ai To Analyze Patent Claim Indefiniteness, Dean Alderucci, Kevin D. Ashley

Articles

In this Article, we describe how to use artificial intelligence (AI) techniques to partially automate a type of legal analysis, determining whether a patent claim satisfies the definiteness requirement. Although fully automating such a high-level cognitive task is well beyond state-of-the-art AI, we show that AI can nevertheless assist the decision maker in making this determination. Specifically, the use of custom AI technology can aid the decision maker by (1) mining patent text to rapidly bring relevant information to the decision maker attention, and (2) suggesting simple inferences that can be drawn from that information.

We begin by summarizing the …

Redefining Roles And Duties Of The Transactional Lawyer: A Narrative Approach, Lori D. Johnson

Scholarly Works

Today’s transactional lawyers perform myriad tasks for their clients, including structuring, drafting, conceptualizing, negotiating, and executing the complex, risky, and often cutting-edge transactions their clients bring to the table. On the other side of that table, often sits another team of sophisticated transactional lawyers. These opposing counsel are armed for battle over every nuance, every word, every representation, every deliverable, and every obligation their client is poised to undertake or agree to. Therefore, modern transactional lawyers must behave as advocates and explore new modes of persuasion. As a response, scholars have begun to propose that transactional lawyers employ methods of …

Elm In The Courtroom: Application To Trial Juries, Natalie Claire Hopkins

Communication Studies

No abstract provided.

Teaching Law And Digital Age Legal Practice With An Ai And Law Seminar: Justice, Lawyering And Legal Education In The Digital Age, Kevin D. Ashley

Articles

A seminar on Artificial Intelligence ("Al") and Law can teach law students lessons about legal reasoning and legal practice in the digital age. Al and Law is a subfield of Al/computer science research that focuses on designing computer programs—computational models—that perform legal reasoning. These computational models are used in building tools to assist in legal practice and pedagogy and in studying legal reasoning in order to contribute to cognitive science and jurisprudence. Today, subject to a number of qualifications, computer programs can reason with legal rules, apply legal precedents, and even argue like a legal advocate.

This article provides a …

Computer-Supported Peer Review In A Law School Context, Kevin D. Ashley, Ilya Goldin

Articles

Legal instructors have been urged to incorporate peer reviewing into law school courses as a way to provide students much needed feedback. Peer review can benefit legal education, but only if law school instructors adopt peer review on a large scale, and for that, computer-supported peer review systems are crucial. These web-based systems orchestrate the mechanics of students submitting written assignments on-line and distributing them to other students for anonymous review, making it considerably easier for instructors to manage.

Beyond the problem of orchestrating mechanics, however, a deeper obstacle to widespread acceptance of peer review in legal education is the …

Computer Models For Legal Prediction, Kevin D. Ashley, Stephanie Bruninghaus

Articles

Computerized algorithms for predicting the outcomes of legal problems can extract and present information from particular databases of cases to guide the legal analysis of new problems. They can have practical value despite the limitations that make reliance on predictions risky for other real-world purposes such as estimating settlement values. An algorithm's ability to generate reasonable legal arguments also is important. In this article, computerized prediction algorithms are compared not only in terms of accuracy, but also in terms of their ability to explain predictions and to integrate predictions and arguments. Our approach, the Issue-Based Prediction algorithm, is a program …

Capturing The Dialectic Between Principles And Cases, Kevin D. Ashley

Articles

Theorists in ethics and law posit a dialectical relationship between principles and cases; abstract principles both inform and are informed by the decisions of specific cases. Until recently, however, it has not been possible to investigate or confirm this relationship empirically. This work involves a systematic study of a set of ethics cases written by a professional association's board of ethical review. Like judges, the board explains its decisions in opinions. It applies normative standards, namely principles from a code of ethics, and cites past cases. We hypothesized that the board's explanations of its decisions elaborated upon the meaning and …

The Narratives Of Cyberspace Law (Or, Learning From Casablanca), Michael J. Madison

Articles

Cyberspace scholars have wrestled extensively with the question of the "right" metaphorical approach to the Internet, in order to guide legal and policy decisions. Literary theorists have wrestled with the perception that cyberspace undermines conventional ideas about narrative. This Essay suggests that each group could learn from the other. Cyberspace tells a better story than literary scholars believe, and the lawyers should pay more attention to the narrative attributes of cyberspace. To illustrate the argument, the Essay proposes a specific story framework for cyberspace: the film Casablanca.

Designing Electronic Casebooks That Talk Back: The Cato Program, Kevin D. Ashley

Articles

Electronic casebooks offer important benefits of flexibility in control of presentation, connectivity, and interactivity. These additional degrees of freedom, however, also threaten to overwhelm students. If casebook authors and instructors are to achieve their pedagogical goals, they will need new methods for guiding students. This paper presents three such methods developed in an intelligent tutoring environment for engaging students in legal role-playing, making abstract concepts explicit and manipulable, and supporting pedagogical dialogues. This environment is built around a program known as CATO, which employs artificial intelligence techniques to teach first-year law students how to make basic legal arguments with cases. …