PoliLegalLM:政治与法律领域大型语言模型的技术报告
PoliLegalLM: A Technical Report on a Large Language Model for Political and Legal Affairs
AI总结:
本文提出PoliLegalLM,通过统一训练框架提升法律知识和推理能力,针对法律领域挑战实现高性能表现。
摘要:
大型语言模型(LLMs)在通用领域任务中取得了显著成功,但其直接应用于法律领域仍面临挑战,原因包括虚构的法律引文、知识覆盖不完整以及推理能力薄弱。为了解决这些问题,我们提出了PoliLegalLM,一个专门针对政治和法律应用的领域模型。我们的方法采用统一的训练框架,整合了持续预训练、渐进监督微调和基于偏好的强化学习,以共同增强法律知识基础、任务对齐和推理能力。我们构建了一个大规模、高质量的法律语料库,并设计了一个结构化的后训练流程,使模型能够有效学习领域特定的知识并适应多样的法律任务。我们在三个代表性基准上评估了PoliLegalLM,包括LawBench、LexEval和一个现实世界的数据集PoliLegal。实验结果表明,PoliLegalLM在性能上表现强劲且一致,优于类似规模的竞争对手,并在显著更大的模型中保持高度竞争力,同时在现实世界法律场景中取得了最佳结果。这些结果突显了我们训练范式的有效性,以及领域特定LLM在现实法律应用中的实际价值。
英文摘要:
Large language models (LLMs) have achieved remarkable success in general-domain tasks, yet their direct application to the legal domain remains challenging due to hallucinated legal citations, incomplete knowledge coverage, and weak structured reasoning. To address these issues, we propose PoliLegalLM, a domain-specific large language model tailored for political and legal applications. Our approach adopts a unified training framework that integrates continued pretraining, progressive supervised fine-tuning, and preference-based reinforcement learning to jointly enhance legal knowledge grounding, task alignment, and reasoning capability. We construct a large-scale, high-quality legal corpus and design a structured post-training pipeline, enabling the model to effectively learn domain-specific knowledge and adapt to diverse legal tasks. We evaluate PoliLegalLM on three representative benchmarks, including LawBench, LexEval, and a real-world dataset, PoliLegal. Experimental results demonstrate that PoliLegalLM achieves strong and consistent performance, outperforming competitive models of similar scale and remaining highly competitive with significantly larger models, while achieving the best results on real-world legal scenarios. These results highlight the effectiveness of our training paradigm and the practical value of domain-specific LLMs for real-world legal applications.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。