WisdomInterrogatory (LuWen): An Open-Source Legal Large Language Model Technical Report
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918437697093632 |
|---|---|
| author | Wu, Yiquan Liu, Yuhang Liu, Yifei Li, Ang Zhou, Siying Kuang, Kun Wu, Fei |
| author_facet | Wu, Yiquan Liu, Yuhang Liu, Yifei Li, Ang Zhou, Siying Kuang, Kun Wu, Fei |
| contents | Large language models have demonstrated remarkable capabilities across a wide range of natural language processing tasks, yet their application in the legal domain remains challenging due to the specialized terminology, complex reasoning requirements, and rapidly evolving legal knowledge involved. In this paper, we present WisdomInterrogatory (LuWen), an open-source Chinese legal language model built upon the Baichuan foundation model through three key techniques: continual pre-training on a large-scale legal corpus, supervised fine-tuning with carefully curated legal instruction data, and retrieval-augmented generation integrated with a comprehensive legal knowledge base. We evaluate LuWen on five representative legal tasks spanning both prediction and generation settings, including legal judgment prediction, judicial examination, legal text summarization, law article question answering, and judicial decision reasoning. Experimental results show that LuWen outperforms several strong baselines, demonstrating the effectiveness of our approach in adapting general-purpose language models to the legal domain. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_06737 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | WisdomInterrogatory (LuWen): An Open-Source Legal Large Language Model Technical Report Wu, Yiquan Liu, Yuhang Liu, Yifei Li, Ang Zhou, Siying Kuang, Kun Wu, Fei Computation and Language Artificial Intelligence Large language models have demonstrated remarkable capabilities across a wide range of natural language processing tasks, yet their application in the legal domain remains challenging due to the specialized terminology, complex reasoning requirements, and rapidly evolving legal knowledge involved. In this paper, we present WisdomInterrogatory (LuWen), an open-source Chinese legal language model built upon the Baichuan foundation model through three key techniques: continual pre-training on a large-scale legal corpus, supervised fine-tuning with carefully curated legal instruction data, and retrieval-augmented generation integrated with a comprehensive legal knowledge base. We evaluate LuWen on five representative legal tasks spanning both prediction and generation settings, including legal judgment prediction, judicial examination, legal text summarization, law article question answering, and judicial decision reasoning. Experimental results show that LuWen outperforms several strong baselines, demonstrating the effectiveness of our approach in adapting general-purpose language models to the legal domain. |
| title | WisdomInterrogatory (LuWen): An Open-Source Legal Large Language Model Technical Report |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2604.06737 |