Program

08:30-09:00 Registration

09:00-10:30 Workshops 1

10:30-11:00 Coffee Break

11:00-12:00 Workshops 2

12:00-13:00 Lunch

13:00-14:30 Workshops 3

14:30-16:00 Workshops 4

16:00-16:30 Coffee Break

16:30-18:00 Workshops 5

18:00 Welcome Reception

08:30-09:00 Registration

09:00-09:30 Opening and Welcome (Radim Polcak, Katie Atkinson, Jakub Harasta, Jaromir Savelka)

09:30-10:30 Case-Based Reasoning in the Legal Domain (chair: Kevin Ashley)

• Case Frames and Case-Based Arguments in Statutory Interpretation (Long) Michał Araszkiewicz
• An Application of Case-Based Reasoning to Decision-Making in Dutch Administrative Law (Long) Joep Nouwens, Annemarie Borg and Henry Prakken
• A Case-Based-Reasoning Analysis of the COMPAS Dataset (Long) Wijnand van Woerkom, Davide Grossi, Henry Prakken and Bart Verheij

10:30-11:00 Coffee Break

11:00-12:00 What Information Does an Algorithmic Legal Judgement Prediction Give? (Keynote by Henry Prakken)

Research on algorithms for legal judgement prediction is booming and it is often claimed that such algorithms can be useful for judges, lawyers and citizens involved in a particular court case. In this talk I will challenge these claims and argue that they partly confuse the task of predicting decisions with the task of taking decisions, partly misinterpret current research on algorithms for legal judgement prediction and partly suffer from the well-known problem of the reference class. I will then go on to claim that there is no meaningful way in which the use of algorithms for legal judgement prediction can increase the consistency and predictability of judicial decision-making.

Henry Prakken is a professor of AI and Law in the Responsible AI group of the Department of Information and Computing Sciences at Utrecht University. His main research interests concern AI and Law and computational models of argumentation. He is a past president of the International Association for AI and Law (IAAIL), of the JURIX Foundation for Legal Knowledge-Based Systems and of the steering committee of the COMMA conferences on Computational Models of Argument. He is on the editorial board of several journals, including Artificial Intelligence and Law. Between 2017 and 2022 he was an associate editor of Artificial Intelligence.

12:00-13:00 Lunch

13:00-14:30 Large Language Models in Legal Services (chair: Adam Wyner)

• Getting in the Door: Streamlining Intake in Civil Legal Services with Large Language Models (Long) Quinten Steenhuis and Hannes Westermann
• Robots in the Middle: Evaluating LLMs in Dispute Resolution (Long) Jinzhe Tan, Hannes Westermann, Nikhil Reddy Pottanigari, Jaromír Šavelka, Sébastien Meeùs, Mia Godet and Karim Benyekhlef
• Prosecutorial Outcome Predication with LoRA and QLoRA (Short) Kuo-Chun Chien, Chia-Hui Chang, Huai-Hsuan Huang and Jo-Chi Kung
• ConsRAG: Minimize LLM Hallucinations in the Legal Domain (Short) Ha-Thanh Nguyen and Ken Satoh
• Impacts of Continued Legal Pre-Training and IFT on LLMs’ Latent Representations of Human-Defined Legal Concepts (Short) Shaun Ho
• InSaAF: Incorporating Safety through Accuracy and Fairness - Are LLMs ready for the Indian Legal Domain? (Short) Yogesh Tripathi, Raghav Donakanti, Sahil Girhepuje, Ishan Kavathekar, Bhaskara Hanuma, Gokul Krishnan, Anmol Goel, Shreya Goyal, Balaraman Ravindran and Ponnurangam Kumaraguru

14:30-16:00 Legal Document Analysis (chair: Hannes Westermann)

• Using LLMs to Discover Legal Factors (Long) Morgan Gray, Jaromir Savelka, Wesley Oliver and Kevin Ashley
• Leveraging LLM for Identification and Extraction of Normative Statements (Long) May Myo Zin, Ken Satoh and Georg Borges
• Detecting Vague Clauses in Privacy Policies: the Analysis of Data Categories using BERT Models and LLMs (Long) Giulia Grundler, Rūta Liepiņa, Mariaceleste Musicco, Francesca Lagioia, Andrea Galassi, Giovanni Sartor and Paolo Torroni
• Legal Chunking: Evaluating Methods for Effective Legal Text Retrieval (Short) Andrea Filippo Ferraris, Davide Audrito, Giovanni Siragusa and Alessandro Piovano
• Optimizing Keyphrase Extraction for Court Decisions Using Legal References (Short) Zoltán Szoplák, Dávid Varga and Peter Gurský

16:00-16:30 Coffee Break

16:30-18:00 Legal Argumentation (chair: Giovanni Sileno)

• Unravelling the ECHR: Components of Legal Case Analysis (Long) Jack Mumford, Katie Atkinson and Trevor Bench-Capon
• Values and Factor Ascription Arguments (Long) Tomasz Zurek, Adam Wyner and Trevor Bench-Capon
• Dispute Resolution in Legal Mediation with Quantitative Argumentation (Short) Xiao Chi
• Annotating Legal Argument Schemes: A Parametric Approach (Short) Frank Goossens, José Plug and Jean Wagemans

19:00 Dinner

08:30-09:00 Registration

09:00-10:30 Legal Information Retrieval (chair: Ken Satoh)

• Hybrid Legal Norm Retrieval: Leveraging Knowledge Graphs and Textual Representations (Long) Sabine Wehnert, Visakh Padmanabhan and Ernesto William De Luca
• Citation Anchor Text for Improving Precedent Retrieval: An Experimental Study on Indian Legal Documents (Long) Gaurang Patil, Bhoomeendra Singh Sisodiya, P. Krishna Reddy and K.V.K. Santhy
• Fighting the Knowledge Representation Bottleneck with Large Language Models (Long) Marco Billi, Marco Sanchi and Giuseppe Pisano
• Combining Network and Text to Provide Legal Pincites (Short) Nicolas Garneau, Henrik Olsen Palmer, Antoine Corduant and Fabien Tarissan

10:30-11:00 Coffee Break

11:00-12:00 Should we expect translation to solve legal cases? (Keynote by Ondrej Bojar)

After a quick summary of the decades-long machine translation research that preceded the Transformer model, I will primarily focus on evaluation fallacies that easily happen when working with deep neural networks and the Transformer model in particular. Transformers, in the form of large language models, are regarded as the silver bullet for a very broad range of language processing and also general language understanding tasks. The main goal of my talk will be to remind you of the limitations of Transformers, to warn about the often unjustified expectations, and to highlight some best practices in experiment design.

Ondrej Bojar is a professor and machine translation researcher at the Institute of Formal and Applied Linguistics at Charles University in Prague. His research interests include interactive machine translation, machine translation post-editing, and psycholinguistic aspects of machine translation. He co-authored Moses, a system for statistical machine translation and is a long-term organizer of WMT: Conference on Machine Translation.

12:00-13:00 Lunch

13:00-14:30 Knowledge Representation and Semantic Technologies (chair: Monica Palmirani)

• Norm Compliance in Reinforcement Learning Agents via Restraining Bolts (Long) Emery Neufeld, Agata Ciabattoni and Radu Florin Tulcan
• Automating Fundamental Right Impact Assessment: An Open Experiment (Long) Xinyue Zhang, Vanja Skoric and Giovanni Sileno
• How to Manage My Data? With Machine-Interpretable GDPR Rights! (Short) Beatriz Esteves, Harshvardhan J. Pandit, Paul Ryan and Georg Philip Krog
• Ontology-based Approach for Mapping Concepts and Requirements from Regulations and Standards: The Case of the EU AI Act and International Standards (Short) Julio Hernandez, Delaram Golpayegani and Dave Lewis
• Design of a Quality Management System Based on the EU AI Act (Short) Henryk Mustroph and Stefanie Rinderle-Ma
• Combining Rule-Based and Machine Learning Methods for Efficient Information Extraction from Enforcement Decisions (Short) Harry Nan, Maarten Marx and Johan Wolswinkel

14:30-16:00 Rule-Based Reasoning in the Legal Domain (chair: Michal Araszkiewicz)

• Decision Support in Law: From Formalizing Rules to Reasoning with Justification (Long) Jeremy Bouche-Pillon, Nathalie Aussenac-Gilles, Yannick Chevalier and Pascale Zaraté
• Modeling Judicial Discretion with Nuanced Permissions (Long) Josephine Dik and Réka Markovich
• When Precedents Clash (Long) Cecilia Di Florio, Huimin Dong and Antonino Rotolo
• On Conflicts and Satisfiability in Metric Timed Normative Logics (Short) Karam Kharraz, Martin Leucker and Gerardo Schneider
• Conflict Analysis for Timed Automata (Short) Shaun Azzopardi and Gordon J. Pace

16:00-16:30 Coffee Break

16:30-18:00 Legal Applications (chair: Katie Atkinson)

• Draft Better Contracts – Detecting Inconsistent Clauses in Stipula (Long) Cosimo Laneve, Alessandro Parenti and Giovanni Sartor
• Automated Semantic Annotation Pipeline for Brazilian Judicial Decisions (Long) Melissa Zorzanelli Costa, Dylan Faria Robson, Thiago Baiense Peçanha Vieira, Giancarlo Guizzardi, Jean-Rémi Bourguet and João Paulo Almeida
• A Narrative Assistant for Traffic Accidents Based on Large Language Models (LLM) (Long) Jo-Chi Kung, Huai-Hsuan Huang, Kuo-Chun Chien and Chia-Hui Chang
• Legal-Emotional BATNA: AI Chatbot Addressing Divorce Legalities and Emotional Complexities, and Research of Social Implementation in Japan (Short) Kohei Oshio
• Building Applications with Purpose: Bridging Human-Centered Design and Human-Centered Artificial Intelligence in Legal Tech with the Double Diamond (Short) Sabine Wehnert and Ernesto William De Luca

• DIREGA – Building Decision Support for German Register Law Axel Adrian, Osman Anil Basaran, Nathan Dykes, Stephanie Evert, Michael Gritz, Merlin Humml, Michael Kohlhase, Andreas Maier, Stephan Prettner, Max Rapp, Lutz Schröder, Verena Stürmer and Johannes Lindner
• Harmonizing AI Governance: Profiling ISO/IEC 5259 to Meet the EU AI Act Requirements Kuruvilla George Aiyankovil and David Lewis
• Legal Question Answering based on Logical Reasoning in Large Pretrained Language Models Joseph Dimos and Eva Fourel
• Structured Legal Argumentation with LLMs: A Study in Landlord-Tenant Law Gregoire Fournier and Daniel Linna
• Beyond Reasonable Doubt: A Logical Framework for Criminal Procedural Permissions Guido Governatori and Antonino Rotolo
• Similar Phrases for Cause of Actions of Civil Cases Ho-Chien Huang and Chao-Lin Liu
• A Legal Assistant for Accountable Decision-Making Adam Kaczmarczyk, Tomer Libal and Aleksander Smywiński-Pohl
• Addressing causal puzzles in law through argumentation Rūta Liepiņa, Giuseppe Pisano and Giovanni Sartor
• AI in Healthcare: Navigating Legal Risk Assessment with JusticeBot Sébastien Meeùs, Valentina Dalla Giovanna, Samyar Janatian, Hannes Westermann, Karim Benyekhlef and Grégory Lewkowicz
• A Multi-Stage Prompting and RAG Approach to Generating Legal Analysis in Common Law Systems Titus T. H. Ng, Tien-Hsuan Wu, Benjamin Minhao Chen, Yongxi Chen and Ben Kao
• Towards Hybrid Assessment Methodologies for Large Language Models in the Legal Domain: Human-Grounded Augmentation of Automatic Evaluation Marco Sanchi and Tereza Novotná
• Explainable AI for Real Legal Judgments: Sentencing Model and Salience Maps for Text Hsuan-Lei Shao, Wei-Hsin Wang and Sieh-Chuen Huang
• A Legal Visualisation Tool Using Normative Diagrams Bianca Steffes and Diogo Sasdelli
• TENJI: A Textbook Entity Network and Jurisprudence Interface Sabine Wehnert, Pramod Kumar Bontha, Kilian Lüders, Bent Stohlmann and Ernesto William De Luca
• LUMI: Legal Understanding and Matching through Interactive Highlighting Sabine Wehnert, Visakh Padmanabhan and Ernesto William De Luca
• LeReRAG: Measuring Legal Relevance in Retrieval Augmented Generation Applications Gineke Wiggers and Christian Hartz