Search papers, labs, and topics across Lattice.
This paper introduces Luwen, an open-source Chinese legal language model, built upon the Baichuan foundation model. The model is trained using continual pre-training on a large legal corpus, supervised fine-tuning with legal instruction data, and retrieval-augmented generation with a legal knowledge base. Experiments across five legal tasks show Luwen outperforms strong baselines, demonstrating effective adaptation of general LLMs to the legal domain.
Open-source Luwen shows that adapting general-purpose LLMs with legal-specific data and retrieval augmentation can yield significant performance gains on complex Chinese legal tasks.
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 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.
