All times are in CET time zone
| 09:00 - 10:30 | Session 1 |
| 09:00 - 09:15 | Workshop opening |
| 09:15 - 10:10 | Invited Talk: The Abstraction Fallacy in Law Mireille Hildebrand |
| 10:10 - 10:20 | A Dataset of Motion-Response Text Pairs from US District Court Cases for Legal Judgment Prediction Damian Curran, Eduard Hovy, Lea Frermann |
| 10:20 - 10:30 | Evaluating LLMs on Explicit Knowledge of Italian Legal Concepts Mattia Proietti, Lucia Passaro, Alessandro Lenci |
| 10:30 - 11:00 | Break |
| 11:00 - 12:30 | Session 2 |
| 11:00 - 11:10 |
NELSR: A Nepali Legal Benchmark for Case-to-Statute Retrieval
Anjan Parajuli, Darshan Kunwar |
| 11:10 - 11:20 |
LegalPincite: Multi-level Legal Information Retrieval Dataset
Theresia Veronika Rampisela, Henrik Palmer Olsen, Giovanni Colavizza |
| 11:20 - 11:30 |
GreekBarRetrieval: A Benchmark for Greek Statutory Retrieval
Ernest Beta, Odysseas S. Chlapanis, Dimitris Galanis, Ion Androutsopoulos |
| 11:30 - 11:40 |
Deka Retrieval: Component-Level Criteria for Mining Legal Case Pairs in Thai Supreme Court Decisions
Pasin Buakhaw, Pawitsapak Akarajaradwong, Chompakorn Chaksangchaichot |
| 11:40 - 11:50 |
LegalBench.PT: A Benchmark for Portuguese Law
Beatriz Canaverde, Telmo Pires, Andre Martins |
| 11:50 - 12:00 |
What Drives an LLM's Legal Reasoning? Measuring Faithfulness at the Concept Level
Yassine Thlija, Lena Held, Ivan Habernal |
| 12:00 - 12:10 |
Legal Experts Disagree With Rationale Extraction Techniques for Explaining ECtHR Case Outcome Classification
Mahammad Namazov, Tomáš Koref, Ivan Habernal |
| 12:10 - 12:20 |
An Empirical Study of Evidence Retrieval for Retrieval Augmented Generation over the Thai Royal Gazette
Pantai Suyasri, Pawitsapak Akarajaradwong, Chompakorn Chaksangchaichot |
| 12:20 - 12:30 |
The EUR-Lex Retrieval Dataset: A Section-Aware and Human-Annotated Dataset for Long-Form Similar Case Retrieval
Christof Koolen |
| 12:30 - 13:30 | Lunch (provided on-site) |
| 13:30 - 15:30 | Session 3 |
| 13:30 - 13:40 |
Structuring license permissiveness from pairwise comparisons
Hamidah Oderinwale, Rachel Hong, David Atkinson, Benjamin Laufer |
| 13:40 - 13:50 |
GapToCompliance: A Taxonomy-Driven Agentic AI Framework for Automated AI Act Gap Analysis and Remediation
Ilias Driouich, Hongliu Cao, Eoin Thomas |
| 13:50 - 14:00 |
Protecting De-identified Documents from Search-based Linkage Attacks
Pierre Lison, Mark Anderson |
| 14:00 - 14:01 |
Privacy Later: Reflections on Design Decisions, Lessons Learned, and Open Problems of the OPP-115 Corpus a Decade After Release
Shomir Wilson, Florian Schaub, Norman Sadeh |
| 14:01 - 14:02 |
Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning
Wei Fan, Zhou Yining, Mufan Zhang, Weng Yanbing, Yiran HU, Tianshi Zheng, Baixuan Xu, Chunyang Li, Jianhui Yang, Haoran Li, Yangqiu Song |
| 14:02 - 14:03 |
Tensions Between Copyright, Contract, Accessibility and Technology in Australia: A Case Study on Legal Information Access
Hunter Briegel, Sumedh Vemuganti, J. Shane Culpepper |
| 14:03 - 14:04 |
From Legal Text to Executable Process: LLM-Based Extraction of DCR Determinations from Danish Administrative Law
Ali Al-Laith, Manex Agirrezabal |
| 14:04 - 14:05 |
OPENER: A Frugal Open-World NER Pipeline for the Legal Domain
Thibault Garel, Faiza Belbachir, Assia Soukane |
| 14:05 - 14:06 |
Persuading the Judge: Adversarial Robustness and RAG Mitigation in LLM-Based Legal Citation Verification
Rohann Rahul Shah, Rishabh Kartik Jawagal, Gowri Srinivasa |
| 14:06 - 14:07 |
Cross-Lingual Legal QA for Vietnamese Labour Law: Retrieval, Translation, and Verifier-Guided Correction
Nguyen Minh Chi, Mo El-Haj, Nguyen Ha Thanh, Dawn Knight, Paul Rayson |
| 14:07 - 14:08 |
Do Small Models Use the Law You Give Them? Measuring Context Use on a Bilingual Bangladesh Legal Benchmark
Moniruzzaman Mahadi, Abrar Mohammed Tanzim Alam, Sayma Siddika Monalisa, Mir Mohammad Asif Abdullah, Swakkhar Shatabda, Md Adnan Arefeen |
| 14:08 - 14:09 |
Completing the Case: The Sufficiency Gap in Legal Retrieval
Sebastien Kawada, Adhiban Arulselvan, Manolis Kellis |
| 14:09 - 14:10 |
Terms and Conditions Apply: Evaluating Consumer LLM Reliability in NDA Interpretation to Investigate the Non-Linear Role of Reasoning
Simeon Sayer, Shaurya Jain Mathur |
| 14:10 - 14:11 |
Evidence-Grounded Contract Clause Classification with Small Language Models
Dina Mohamed Ali, hager hamed abd elrady allam, Hayam Abdelbaset Rezk, Rahatara Ferdousi, Mohammed Anber AbdElhamed |
| 14:11 - 14:12 |
CANLEGALRAGBENCH: Evaluating Retrieval-Augmented Generation on Canadian Case Law
Ethan Zhao, Maksym Taranukhin, Wei Cui, Moira Aikenhead, Vered Shwartz |
| 14:12 - 14:13 |
ARGUS: Role-Aware Event Knowledge Graphs for U.S. Employment-Discrimination Complaints
Sriram Kannan, Swetha Saseendran, Vishnu Vardhan Reddy Kandi, Leslie Barrett, Madhavan Seshadri, Enrico Santus |
| 14:13 - 14:14 |
Retrieval for Legal AI: Complementarity and Cross-Collection Interference in Brazilian Legal Collections
Flavio Soriano, Guilherme Henrique Gomes Evangelista, Celso França, Gisele L. Pappa, Wagner Meira Jr., Marcos André Gonçalves |
| 14:14 - 14:15 |
Cited but Not Consulted: A Counterfactual Audit of Legal Chain-of-Thought Faithfulness
Saisab Sadhu, Shreeyans Arora, Pratinav Seth |
| 14:15 - 14:16 |
Verdict Without the Rule: Diagnosing and Auditing Regulatory Rule Sensitivity in LLM Compliance Systems
Saisab Sadhu, Aadit Sengupta, Vinay kumar Sankarapu, Pratinav Seth |
| 14:16 - 14:17 |
CLARE: A Criminal-Law DSL for Neuro-Symbolic Long-Form Legal Reasoning
Jaehoon Jeong, Jay-Yoon Lee |
| 14:17 - 14:18 |
GRACE: Grounded Adversarial Reasoning over Canadian Law
Jiakang Xu, Wantong Huo, Udom Silparcha, Jonathan H. Chan |
| 14:18 - 14:19 |
What the Public Asked to Change, and What It Would Touch: Complaint-to-Statute Grounding for Thailand's Regulatory Guillotine
Pawitsapak Akarajaradwong, Wuttikrai Lertprasertphakorn, Chompakorn Chaksangchaichot, Sarana Nutanong |
| 14:19 - 14:20 |
Beyond the Single-Expert Ceiling: Localizing LLM-as-Judge Stability on Free-Form Legal Essays
Pawitsapak Akarajaradwong, Wuttikrai Lertprasertphakorn, Chompakorn Chaksangchaichot, Sarana Nutanong |
| 14:20 - 14:21 |
Outside the Four Corners: Charting the Missing Evidence in Korean AI Training-Data License Screening
Jiwoo Lee, Sungwon Chae |
| 14:21 - 14:22 |
FIRAC-APPEALS: A Structured Indian Appellate Judgments Dataset for Summarisation and Reasoning-Aware Legal NLP
Martin Borčin, Joemon M. Jose |
| 14:22 - 14:23 |
Enhancing Legal Reasoning in Pre-trained Language Models via Knowledge Graph-Guided Multi-Task Pre-training
Ibrahim Siddig, Munir Georges |
| 14:23 - 14:24 |
UCVE: Graph Structured Retrieval for Compliance Validation
Emily Chen, Michelle Menachery, Rahul Nenavath, Himanshu Kumar, Amirfarrokh Iranitalab |
| 14:24 - 14:25 |
Right Code, Wrong Reasons: An Audit Trail Benchmark for Customs Classification
Kancharla Aditya Hari, Sai Khadloya, Arghya Bhattacharya, Kumarmanas Nethil |
| 14:25 - 15:30 | Poster Session |
| 15:30 - 16:00 | Break |
| 16:00 - 17:30 | Session 4 |
| 16:00 - 16:15 |
ChildSafeAds Shared Task 2026: Commercial Content in Child-Facing YouTube Videos
Thales Bertaglia, Catalina Goanta, Gerasimos Spanakis, Gunes Acar |
| 16:15 - 16:16 |
thylinao at ChildSafeAds 2026: When the Divisor Is Part of the Hidden Test Set
Maksim Silchenko |
| 16:16 - 16:17 |
AI-Monitors at ChildSafeAds 2026: A Routed Hybrid for Commercial Content in Child-Facing YouTube Videos
Pragyananda sahoo, Vishnu Tripathi, Prakhar joshi, Gaurav Kumar, Neel Mani |
| 16:17 - 16:18 |
What Does More Data Buy? Structurally Dissimilar Voter Ensembles at ChildSafeAds 2026
Philipp Steigerwald, Eric Rudolph, Jens Albrecht |
| 16:18 - 16:19 |
Alphastream at ChildSafeAds 2026: Gated Per-Label Merging and an Advertiser-Precedent Rule for Rare Compliance Classes
Raghavendra Prasad Narayan |
| 16:15 - 16:25 | Q&A Shared Task and Next Steps |
| 16:25 - 16:35 |
Where Experts Disagree, Models Fail: Detecting Implicit Legal Citations in French Court Decisions
Avrile Floro, Tamara Dhorasoo, Soline Pellez, Nils Holzenberger |
| 16:35 - 16:45 |
A Strong Harness Narrows the Model Gap: A Model-Scale Ablation for Legislative Document-to-XML Conversion
Palvika Bansal, Rittika Jindal, Ruichong Wang |
| 16:45 - 16:55 |
Discovering Hierarchical Semantic Structures in EU Regulatory Embeddings: A Comparison of Two K-means Solutions and Their Alignment with EuroVoc
Kayoko Fukasawa |
| 16:55 - 17:05 |
OblEx26: A Multi-Jurisdictional Benchmark for Structured Obligation Extraction from Anti-Money Laundering Regulations
Philip Moore, Giovanni Bandi, Tim Luka Horstmann, Russell Moore, Robert H. Wardrop, Paula Buttery |
| 17:05 - 17:15 |
Building Structured Sentencing Data from Federal Criminal Docket Entries: An Ontology and Entity Extraction Study
David Guecha, Aanan Biswas, Charlotte S. Alexander |
| 17:15 - 17:25 |
The Bluebook as Code: A Deterministic Engine for Legal Citation
The Bluebook as Code: A Deterministic Engine for Legal Citation |
| 17:25 - 17:30 | Closing and Awards |