Legal Summarisation through LLMs: The PRODIGIT Project

08/04/2023
by   Thiago Dal Pont, et al.
0

We present some initial results of a large-scale Italian project called PRODIGIT which aims to support tax judges and lawyers through digital technology, focusing on AI. We have focused on generation of summaries of judicial decisions and on the extraction of related information, such as the identification of legal issues and decision-making criteria, and the specification of keywords. To this end, we have deployed and evaluated different tools and approaches to extractive and abstractive summarisation. We have applied LLMs, and particularly on GPT4, which has enabled us to obtain results that proved satisfactory, according to an evaluation by expert tax judges and lawyers. On this basis, a prototype application is being built which will be made publicly available.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/08/2015

The Role of Pragmatics in Legal Norm Representation

Despite the 'apparent clarity' of a given legal provision, its applicati...
research
07/11/2023

Argumentative Segmentation Enhancement for Legal Summarization

We use the combination of argumentative zoning [1] and a legal argumenta...
research
09/28/2021

Predicting Indian Supreme Court Judgments, Decisions, Or Appeals

Legal predictive models are of enormous interest and value to legal comm...
research
11/10/2019

Searching for Legal Clauses by Analogy. Few-shot Semantic Retrieval Shared Task

We introduce a novel shared task for semantic retrieval from legal texts...
research
07/27/2023

JusticeBot: A Methodology for Building Augmented Intelligence Tools for Laypeople to Increase Access to Justice

Laypeople (i.e. individuals without legal training) may often have troub...
research
07/09/2020

Predicting Court Decisions for Alimony: Avoiding Extra-legal Factors in Decision made by Judges and Not Understandable AI Models

The advent of machine learning techniques has made it possible to obtain...
research
07/29/2020

Robbins and Ardila meet Berstel

In 1996, Neville Robbins proved the amazing fact that the coefficient of...

Please sign up or login with your details

Forgot password? Click here to reset