ASAIL 2025
Automated Semantic Analysis of Information in Legal Texts 2025

Table of Contents

• Preface
  Summary: There were 9 papers submitted for peer-review to this workshop. Out of these, 8 papers were accepted for this volume, 5 as regular papers and 3 as short papers.

Session 1: Evaluating & Specializing LLMs

• Measuring Faithfulness and Abstention: An Automated Pipeline for Evaluating LLM-Generated 3-ply Case-Based Legal Arguments (Long paper) 1-18
  Li Zhang , Morgan Gray , Jaromir Savelka , Kevin D. Ashley
• Semantic Specialization of Legal LLMs via Large-Scale Fine-Tuning on Jurisdictional MCQs (Long paper) 19-31
  Hsuan-Lei Shao
• Semantic Evaluation of Legal Essay Reasoning with Transfer-Learned LLMs: A Crowdsourced Elo Framework (Long paper) 32-46
  Ying-Chu Yu , Hsuan-Lei Shao

Session 2: Structure & Explainability in Legal AI

• Incorporating Legal Structure in Retrieval-Augmented Generation: A Case Study on Copyright Fair Use (Long paper) 47-59
  Justin Ho , Alexandra Colby , William Fisher
• Detecting Purpose Language in State Regulations (Short paper) 60-68
  Chandan Aggarwal , Royce Koh , Cindy Zhang , Matthew Carey , Sylvia Kwakye
• Explainable NLLP: Advancements in Explainable AI for Natural Legal Language Processing (Short paper) 69-82
  Lucas Resck , Felipe Moreno-Vera , Tobias Veiga , Gerardo Paucar , Ezequiel Fajreldines , Guilherme Klafke , Luis Gustavo Nonato , Jorge Poco

Session 3: Neuro-Symbolic & Logical Approaches

• From Legal Texts to Defeasible Deontic Logic via LLMs: A Study in Automated Semantic Analysis (Long paper) 83-100
  Elias Horner , Cristinel Mateis , Guido Governatori , Agata Ciabattoni

Session 4: Information Extraction & Datasets

• What Are the Facts? Automated Extraction of Court-Established Facts from Criminal-Court Opinions (Short paper) 101-117
  Klára Bendová , Tomáš Knap , Jan Černý , Vojtěch Pour , Jaromir Savelka , Ivana Kvapilíková , Jakub Drápal