 Your new post is loading...
|
Scooped by
Stéphane Cottin
August 19, 2024 9:36 AM
|
Ce guide méthodologique a été conçu pour fournir : • une cartographie des gisements d’informations disponibles pour toutes les sources du droit français, du droit de l’Union européenne et du droit international (législation, jurisprudence, doctrine), • une description plus détaillée des données et outils essentiels, accompagnée de trucs et astuces pour une utilisation efficace, • une méthode de travail adaptable à tous les types de recherche et des conseils plus pointus pour des requêtes et investigations spécialisées.Le corps du texte s’accompagne d’outils permettant d’acquérir des compétences en recherche d’information juridique : des copies d’écran illustrent les procédures, des résumés permettent de mémoriser les points essentiels, des focus approfondissent certains aspects plus complexes. Privilégiant la pratique et une approche la plus concrète possible, l’ouvrage devrait être utile à l’étudiant en licence ou master, au professionnel du droit ou de l’information juridique. Au-delà, il devrait intéresser toute personne souhaitant : • se former à la recherche documentaire juridique, • vérifier ou actualiser ses connaissances dans le domaine, • former des étudiants à ce type de recherche, • mesurer l’impact de l’intelligence artificielle sur la recherche d’information juridique.
|
Scooped by
Stéphane Cottin
June 18, 1:12 PM
|
Is Generative AI any good at legal writing? The answer to that question has major implications for legal practice and legal education. If Generative AI
|
Scooped by
Stéphane Cottin
June 17, 4:47 AM
|
Database tracking legal cases where generative AI produced hallucinated citations submitted in court filings.
|
Scooped by
Stéphane Cottin
June 13, 1:46 AM
|
|
Scooped by
Stéphane Cottin
June 10, 1:55 PM
|
|
Scooped by
Stéphane Cottin
June 9, 4:14 PM
|
Legal Research Demystified provides a practical approach to legal research. The textbook guides law students through eight steps to research common law i
|
Scooped by
Stéphane Cottin
June 4, 2:20 AM
|
The Supreme Court of the United States (SCOTUS) issues 10-15 % of its opinions unsigned, concealing authorship. Traditionally, unveiling authors required the po
|
Scooped by
Stéphane Cottin
May 29, 2:12 PM
|
Law school grading practices often conflict with legal research instruction goals. Small class sizes render norm-referenced (curved) grading unreliable, and the
|
Scooped by
Stéphane Cottin
May 27, 3:21 AM
|
This book constitutes the proceedings of the 17th JSAI International Symposia on Artificial Intelligence (JSAI-isAI 2025), held in Osaka, Japan, during May 26–27, 2025. The 27 full papers included in this book were carefully reviewed and selected from 82 submissions. The papers covered a wide range of topics, including AI & law, juris-informatics, natural language processing for scientific documents, Information retrieval for scientific documents, business Informatics, agent-based modeling, AI & security, AI & privacy.
|
Scooped by
Stéphane Cottin
May 21, 1:01 AM
|
This article is a companion to How I Learned to Stop Worrying and Love the Bot: What I Learned About AI and What You Can Too. This a
|
Scooped by
Stéphane Cottin
May 18, 4:18 AM
|
Large language models (LLMs), trained on extensive datasets, demonstrate their exceptional ability to handle textual data to yield desired outputs solely through prompts and demonstrations, eliminating the need for extensive fine-tuning. Despite their potential to change lives, integrating LLMs into the legal domain poses challenges, necessitating high-level reasoning, efficient understanding of complex linguistic structures, and faithful reflection of legal precedents. Tailoring prompting paradigm LLMs through reasoning techniques to address legal nuances enhances their precision and relevance in generating legal text. Despite advancements in language processing, challenges persist, particularly the lack of domain-specific knowledge in LLMs. Approaches such as integrating external information retrieval systems and fine-tuning with domain-specific data aim to mitigate this gap. This research provides a comprehensive exploration of adaptive strategies aimed at increasing the reasoning capabilities of LLMs within the legal domain. The paper delves into various prompt engineering methodologies, approaches to incorporate external knowledge, and frameworks for evaluating LLM responses, with the aim of inspiring further research in prompt engineering specifically tailored for legal applications while addressing prevailing research challenges.
|
Scooped by
Stéphane Cottin
May 7, 1:26 PM
|
The rapid advancement of artificial intelligence (AI) has had a profound impact on nearly every industry, including legal academia. As AI-driven tools like Chat
|
Scooped by
Stéphane Cottin
May 6, 1:34 AM
|
This article, based upon a keynote address by Professor Harry Surden, provides an in-depth overview of the recent advancements in artificial intelligence (AI) s
|
|
Scooped by
Stéphane Cottin
Today, 1:34 AM
|
Long-form legal reasoning remains a key challenge for large language models (LLMs) in spite of recent advances in test-time scaling. We introduce LEXam, a
|
Scooped by
Stéphane Cottin
June 17, 5:25 AM
|
L’association Juriconnexion vous propose un document de présentation sur l’Open Data des décisions judiciaires, la chronologie, les portails consultables et ce que vous pouvez y trouver. Open da quoi ? « La mise à disposition des décisions de justice, plus communément désignée par l’expression « open data des décisions de justice », vise à rendre disponibles à tous, à […]
|
Scooped by
Stéphane Cottin
June 15, 4:04 PM
|
7 JUILLET 1997. - Arrêté royal relatif à la publication [des arrêts et des ordonnances de non-admission] du Conseil d'Etat. (NOTE : Consultation des versions antérieures à partir du 08-08-1997 et mise à jour au 15-06-2011)
|
Scooped by
Stéphane Cottin
June 11, 4:21 PM
|
Legal scholarship is overly abstract and theoretical, making it unhelpful to judges and lawyers. That, at least, is the common critique from the bench. When it
|
Scooped by
Stéphane Cottin
June 10, 1:21 AM
|
In her essay, A New Parlor is Open: Legal Writing Faculty Must Develop Scholarship on Generative AI and Legal Writing, Dr. Kirsten Davis questions the as
|
Scooped by
Stéphane Cottin
June 9, 4:08 PM
|
Almost all users despise The Bluebook, and the twenty-second edition will do little to end this hatred. Despite all of the criticism,
|
Scooped by
Stéphane Cottin
June 4, 2:18 AM
|
We develop an agent-based model to investigate the mechanisms that determine state compliance with European Court of Human Rights judgments. Tasked with upholdi
|
Scooped by
Stéphane Cottin
May 29, 12:23 PM
|
This study investigates whether AI and ML tools can support European legislative drafting with advanced information retrieval using AI and which methods are more effective. The article shows the hybrid methods leveraging the combination of LegalXML-annotate
|
Scooped by
Stéphane Cottin
May 22, 5:29 PM
|
This chapter surveys developments related to the use of generative AI in courts in the United States. It discusses a range of current uses of generativ
|
Scooped by
Stéphane Cottin
May 20, 1:28 AM
|
The publication of court judgments has been long viewed as essential to upholding rule of law and democratic norms. In recent years, there has been also a deman
|
Scooped by
Stéphane Cottin
May 8, 10:46 AM
|
Behind a set of rules in Deontic Defeasible Logic, there is a mapping process of normative background fragments. This process goes from text to rules and implicitly encompasses an explanation of the coded fragments. In this paper we deliver a methodology for \textit{legal coding} that starts with a fragment and goes onto a set of Deontic Defeasible Logic rules, involving a set of \textit{scenarios} to test the correctness of the coded fragments. The methodology is illustrated by the coding process of an example text. We then show the results of a series of experiments conducted with humans encoding a variety of normative backgrounds and corresponding cases in which we have measured the efforts made in the coding process, as related to some measurable features. To process these examples, a recently developed technology, Houdini, that allows reasoning in Deontic Defeasible Logic, has been employed. Finally we provide a technique to forecast time required in coding, that depends on factors such as knowledge of the legal domain, knowledge of the coding processes, length of the text, and a measure of \textit{depth} that refers to the length of the paths of legal references.
|
Scooped by
Stéphane Cottin
May 6, 11:56 PM
|
Factors are a foundational component of legal analysis and computational models of legal reasoning. These factor-based representations enable lawyers, judges, a
|
Scooped by
Stéphane Cottin
May 6, 1:33 AM
|
Factors are a foundational component of legal analysis and computational models of legal reasoning. These factor-based representations enable lawyers, judges, a
|