ASAIL 2025
7th Workshop on Automated Semantic Analysis of Information in Legal Text
2025 June 16
Held in hybrid format in conjunction with ICAIL 2025
Held in hybrid format in conjunction with ICAIL 2025
The ASAIL proceedings will be published later in the year. Accepted papers will be made available prior to the commencement of the workshop.
All times are provided in the CDT (UTC-5) time zone. We will hold the workshop in Room RB150 on site at the Northwestern Pritzker School of Law. The conference link will be distributed to workshop registrants. For information about registration for workshop as well as information concerning the main conference please see the ICAIL website.
The workshop will consist of four paper sessions. Each session will consist of a series of 15 minute presentations (10 minutes + 5 minutes Q&A) and close with a thirty minute panel discussion of key questions and open problems relevant to the session's theme.
For those joining us in person, we will be based in Room RB150 in the Northwestern Pritzker School of Law.
For those joining us online, the zoom link should be emailed to you by the end of Saturday, June 14. Anyone who has registered and not received the link should contact Jack Mumford (details at bottom of page).
09:10 (Paper) Measuring Faithfulness and Abstention: An Automated Pipeline for Evaluating LLM‑Generated 3‑ply Case‑Based Legal Arguments. Li Zhang, Morgan Gray, Jaromir Savelka, Kevin Ashley.
09:25 (Abstract) Semantic Specialization of Legal LLMs via Large‑Scale Fine‑Tuning on Jurisdictional MCQs. Hsuan‑Lei Shao.
09:40 (Abstract) LLMs and Legal Reasoning: Where has Legal Knowledge Gone? Kevin Ashley.
09:55 (Abstract) Semantic Evaluation of Legal Essay Reasoning with Transfer‑Learned LLMs: A Crowdsourced Elo Framework. Ying‑Chu Yu, Hsuan‑Lei Shao .
10:10 Panel discussion on key questions and open problems for Evaluating & Specializing LLMs.
11:10 (Paper) Incorporating Legal Structure in Retrieval‑Augmented Generation: A Case Study on Copyright Fair Use. Justin Ho, Alexandra Colby, William Fisher.
11:25 (Paper) Detecting Purpose Language in State Regulations. Matthew Carey, Chandan Aggarwal, Royce Koh, Cindy Zhang, Sylvia Kwakye.
11:40 (Paper) Explainable NLLP: Advancements in Explainable AI for Natural Legal Language Processing. Lucas Resck, Felipe Moreno-Vera, Tobias Veiga, Gerardo Paucar, Ezequiel Fajreldines, Guilherme Klafke, Luis Gustavo Nonato, Jorge Poco.
11:55 (Abstract) Bridging Statutes and Precedent: A Rule‑Tree & LLM‑Driven Pipeline for Case‑Law Analysis. Hannes Westermann.
12:10 (Abstract) Transparent and trustworthy AI for legal document generation. Gabor Recski.
12:25 Panel discussion on key questions and open problems for Structure & Explainability in Legal AI.
14:00 (Paper) From Legal Texts to Defeasible Deontic Logic via LLMs: A Study in Automated Semantic Analysis. Elias Horner, Cristinel Mateis, Guido Governatori, Agata Ciabattoni.
14:15 (Abstract) Towards a Neuro‑Symbolic Approach to Legal Compliance Checking: Patterns for Deontic Norms Representation and Reasoning. Enrico Francesconi.
14:30 (Abstract) Translating Natural Language Building Regulations into SHACL DL with a LLM. Dominic Love, Adam Wyner.
14:45 (Abstract) A Neuro‑Symbolic Approach to Legal Textual Entailment. Cor Steging, Ludi van Leeuwen.
15:00 Panel discussion on key questions and open problems for Neuro‑Symbolic & Logical Approaches.
16:00 (Paper) What Are the Facts? Automated Extraction of Court‑Established Facts from Opinions of Criminal Courts. Klára Bendová, Tomáš Knap, Jan Černý, Vojtěch Pour, Ivana Kvapilíková, Jaromír Šavelka, Jakub Drápal.
16:15 (Abstract) Unsupervised Learning for Creating Labeled Datasets for Legal Text Classification. Shashank Chakravarthy, Anna Wilbik, Gijs van Dijck.
16:30 (Abstract) Czech Constitutional Court Decisions Semantic Search. Tereza Novotná.
16:45 (Abstract) Citation Context - Intelligent Datasets for Case Law Retrieval. Jack Mumford.
17:00 (Abstract) Generating Legal Problems for Access to Justice: Exploring the Use of GenAI for Legal Query Formulation. Lyra Hoeben‑Kuil.
17:15 Panel discussion on key questions and open problems for Information Extraction & Datasets.