# NOWJ@COLIEE 2025: A Multi-stage Framework Integrating Embedding Models and Large Language Models for Legal Retrieval and Entailment

arXiv: https://arxiv.org/abs/2509.08025 · HTML: https://mlsanity.com/paper/2509.08025/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 20 references that are in the map.
- First posted on arXiv 9 Sep 2025.

## Builds on (most cited first, 7 of 7)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [How Does NLP Benefit Legal System: A Summary of Legal Artificial Intelligence](https://mlsanity.com/paper/2004.12158/) (2020)
- [Towards an In-Depth Comprehension of Case Relevance for Better Legal Retrieval](https://mlsanity.com/paper/2404.00947/) (2024)
- [Japanese Tort-case Dataset for Rationale-supported Legal Judgment Prediction](https://mlsanity.com/paper/2312.00480/) (2023)

## Built on by (most cited first, 1 of 1)

- [Self-Verification is All You Need To Pass The Japanese Bar Examination](https://mlsanity.com/paper/2601.03144/) (2026)

## Abstract (arXiv)

This paper presents the methodologies and results of the NOWJ team's participation across all five tasks at the COLIEE 2025 competition, emphasizing advancements in the Legal Case Entailment task (Task 2). Our comprehensive approach systematically integrates pre-ranking models (BM25, BERT, monoT5), embedding-based semantic representations (BGE-m3, LLM2Vec), and advanced Large Language Models (Qwen-2, QwQ-32B, DeepSeek-V3) for summarization, relevance scoring, and contextual re-ranking. Specifically, in Task 2, our two-stage retrieval system combined lexical-semantic filtering with contextualized LLM analysis, achieving first place with an F1 score of 0.3195. Additionally, in other tasks--including Legal Case Retrieval, Statute Law Retrieval, Legal Textual Entailment, and Legal Judgment Prediction--we demonstrated robust performance through carefully engineered ensembles and effective prompt-based reasoning strategies. Our findings highlight the potential of hybrid models integrating traditional IR techniques with contemporary generative models, providing a valuable reference for future advancements in legal information processing.