Professor Minh Le Nguyen's team, Computing Science Research Area, achieved the highest performance in three categories--Task 1 (Legal Case Retrieval), Task 3 (Statute Law Retrieval), and the Tort Prediction subtask of the Pilot Task (Legal Judgment Prediction for Japanese Tort cases)--at the 12th Competition on Legal Information Extraction and Entailment (COLIEE 2025).

COLIEE is an international competition that evaluates the accuracy of AI-based information retrieval and legal reasoning using legal documents such as case law and statutes. The competition aims to improve the efficiency of judicial procedures and enhance access to legal systems. The 12th edition of the competition, COLIEE 2025, was held on June 20, 2025, at Northwestern University in Chicago, USA.
In COLIEE 2025, a total of five tasks were presented: Task 1 and Task 2 based on case law, Task 3 and Task 4 based on statutory law, and a pilot task (LJPJT25) focusing on Japanese tort law (Article 709 of the Civil Code of Japan). The pilot task was introduced for the first time and provided a sandbox environment where researchers could develop and evaluate new methods using actual case data on torts from Japanese courts.
COLIEE 2025 was held in conjunction with ICAIL 2025 (International Conference on Artificial Intelligence and Law), a leading international conference in the field of AI and law.

※Reference：COLIEE 2025
　　　　　　　ICAIL 2025

■Date Awarded
June 20, 2025

【Task 1・3】
■Team Name and Members
JNLP：Hai Nguyen, Hiep Nguyen, Trang Pham, Minh Nguyen, An Trieu, Dinh-Truong Do, Nguyen-Khang Le, Le-Minh Nguyen

■Title
Hybrid Large Language Model-based Framework for Legal Information Retrieval and Entailment

■Abstract
This paper presents the JNLP team's approaches for the COLIEE 2025 competition, addressing all four legal information processing tasks: case law retrieval, case law entailment, statute law retrieval, and statute law entailment. Our systems leverage a hybrid framework that synergistically combines classical information retrieval (IR) pipelines, fine-tuned Transformer-based models, and instruction-tuned Large Language Models (LLMs) for deep legal reasoning. For case law retrieval (Task 1), we enhance a proposition-based ranking model by integrating lexical and structural-semantic features. For case law entailment (Task 2), we adopt a two-stage pipeline: we fine-tune re-rankers with hard-negative sampling and refine predictions using few-shot prompted LLMs. In statute law retrieval (Task 3), we implement a three-stage pipeline consisting of embedding-based pre-retrieval, LoRA/QLoRA-based fine-tuning, and model ensembling. For statute law entailment (Task 4), we explore zero-shot, few-shot, and reasoning ensemble prompting using models like Qwen2-72B to generate well-justified yes/no answers. Experimental results show that our methods achieve top-tier performance across multiple tasks in the official COLIEE 2025 evaluation. Our findings highlight the practicality and effectiveness of integrating lightweight IR models with large-scale LLMs for high-stakes legal NLP applications.

　

　

【Pilot Task】
■Team Name and Members
CAPTAIN：Dat Nguyen, Minh-Phuong Nguyen, Quang-Huy Chu, Son T. Luu, Nguyen-Hoang Chu, Trung Vo, Le-Minh Nguyen

■Title
Enhancing Legal Text Processing and Structural Analysis with Large Language Models

■Abstract
The legal domain poses unique challenges for information extraction and reasoning due to the intricate structure and domain-specific language of legal texts. To address these challenges, our team, CAPTAIN, leverages recent advances in Large Language Models (LLMs) to enhance legal information processing within the scope of the COLIEE 2025 competition. We participate in four tasks: Legal Case Entailment (Task 2), Statute Law Retrieval (Task 3), Legal Textual Entailment (Task 4), and Legal Judgment Prediction for Japanese Tort Law (Pilot Task). Our approach harnesses the interpretive power of LLMs to analyze and summarize complex legal documents, uncover semantic relationships between legal cases and relevant statutes, and perform contextual reasoning. By leveraging diverse prompting techniques, our approach effectively uncovers implicit relationships between legal cases and their corresponding statutes, thereby enhancing both interpretability and accuracy. Experimental results demonstrate the strength of our method: it achieved first place in the Tort Prediction sub-task of the Pilot Task, and second place in both the Legal Statute Law Retrieval and Rationale Extraction sub-tasks, confirming the potential of LLM-based approaches in legal AI.

■Comment COLIEE 2025 is a prestigious international competition in the field of Legal AI. This year, Nguyen Lab achieved the highest overall performance, securing first place in three out of five tasks. These outstanding results reflect the dedication and talent of our students, whose efforts continue to advance our contributions to the Legal AI domain. We are deeply honored to receive this recognition and sincerely thank JAIST for providing an exceptional research environment that supports our work. This achievement serves as a strong source of encouragement for our students and all members of the lab, inspiring us to pursue further research and strive for even greater accomplishments in the future.

August 20, 2025