The paper presents a preliminary analysis of an experiment conducted by Frank Bold, a Czech expert group, to explore user interactions with GPT-4 for addressing legal queries. Between May 3, 2023, and July 25, 2023, 1,252 users submitted 3,847 queries. Unlike studies that primarily focus on the accuracy, factuality, or hallucination tendencies of large language models (LLMs), our analysis focuses on the user query dimension of the interaction. Using GPT-4o for zero-shot classification, we categorized queries on (1) whether users provided factual information about their issue (29.95%) or not (70.05%), (2) whether they sought legal information (64.93%) or advice on the course of action (35.07\%), and (3) whether they imposed requirements to shape or control the model's answer (28.57%) or not (71.43%). We provide both quantitative and qualitative insight into user needs and contribute to a better understanding of user engagement with LLMs.

This paper addresses a critical gap in legal analytics by developing and applying a novel taxonomy for topic modelling summary judgment cases in the United Kingdom. Using a curated dataset of summary judgment cases, we use the Large Language Model Claude 3 Opus to explore functional topics and trends. We find that Claude 3 Opus correctly classified the topic with an accuracy of 87.10%. The analysis reveals distinct patterns in the application of summary judgments across various legal domains. As case law in the United Kingdom is not originally labelled with keywords or a topic filtering option, the findings not only refine our understanding of the thematic underpinnings of summary judgments but also illustrate the potential of combining traditional and AI-driven approaches in legal classification. Therefore, this paper provides a new and general taxonomy for UK law. The implications of this work serve as a foundation for further research and policy discussions in the field of judicial administration and computational legal research methodologies.

In an new column, "Tech-Enabled A2J", we will take a look at how legal start-ups and legal technology innovations are impacting the push toward better Access to Justice for more citizens. Whereas LSOs have found past success in reaching clients through basic tools like texting, they are now moving to more advanced platforms like document automation to better streamline internal processes. Some are even going one step further by embarking on artificial intelligence (AI) and machine learning (ML) projects to determine how they can help address the 86% of civil legal problems reported by low-income Americans that aren't fully resolved. Access to justice starts with literal access: figuring out how clients best receive, digest, and act on legal information. On the lower-tech end, text messaging has proven to be a successful tool for reaching those in need.

AI-powered chatbots come with many benefits for the businesses that adopt them, but in some instances, they can have greater impact for the everyday user. In this blog, we list four recent articles giving examples of where AI-powered applications and chatbots have been put into practice to help customers and the common man. The developer of the'world's first robot lawyer' application, which helped overturn more than one-hundred parking fines, is now adapting the functionality of the integrated chatbot to provide legal aid to refugees seeking asylum in the US and Canada, as well as asylum support in the UK. The original DoNotPay AI-powered application gives legal aid through a simple chat interface, where a chatbot asks a series of questions to help determine which application a refugee needs to fill out and whether they are eligible for asylum protection under international law. After this, the chatbot takes note of the relevant details required for asylum applications in the US or Canada, auto-fills the application form and sends.

An artificial intelligence platform, called Rechtwijzer, could soon give lawyers in Australia a run for their money by being called on in legal battlegrounds like divorce, custody, employment and debt disputes. National Legal Aid and RMIT University are showcasing Dutch technology that could make time-consuming and expensive court conflict a thing of the past. The technology would be similar to eBay's dispute resolution service that helps people log on, rather than lawyer up. The dispute resolution robot was born in the Netherlands and can mediate everything from divorces, tenancy disputes, and employment, debt and consumer matters. For custody matters, for example, it will ask the ages of the children to be sensitive to their development needs.