LLM post-training has primarily relied on large text corpora and human feedback, without capturing the structure of domain knowledge. This has caused models to struggle dealing with complex reasoning tasks, especially for high-stakes professional domains. In Law, reasoning requires deep understanding of the relations between various legal concepts, a key component missing in current LLM post-training. In this paper, we propose a knowledge graph (KG)-assisted approach for enhancing LLMs' reasoning capability in Legal that is generalizable to other high-stakes domains. We model key legal concepts by following the \textbf{IRAC} (Issue, Rule, Analysis and Conclusion) framework, and construct a KG with 12K legal cases. We then produce training data using our IRAC KG, and conduct both Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) with three state-of-the-art (SOTA) LLMs (30B, 49B and 70B), varying architecture and base model family. Our post-trained models obtained better average performance on 4/5 diverse legal benchmarks (14 tasks) than baselines. In particular, our 70B DPO model achieved the best score on 4/6 reasoning tasks, among baselines and a 141B SOTA legal LLM, demonstrating the effectiveness of our KG for enhancing LLMs' legal reasoning capability.

翻译：LLM后训练主要依赖于大规模文本语料库和人类反馈，未能捕捉领域知识的结构。这导致模型在处理复杂推理任务时存在困难，尤其是在高风险的专业领域。在法律领域，推理需要对各种法律概念之间的关系有深入理解，而这是当前LLM后训练中缺失的关键组成部分。本文提出一种知识图谱辅助的方法，用于增强LLM在法律领域的推理能力，该方法可推广至其他高风险领域。我们依据\textbf{IRAC}框架对关键法律概念进行建模，并构建了包含12K个法律案例的知识图谱。随后利用该IRAC知识图谱生成训练数据，并对三种最先进的LLM（30B、49B和70B）进行监督微调和直接偏好优化，这些模型在架构和基础模型家族上具有差异性。我们的后训练模型在4/5多样化法律基准测试（14项任务）中取得了优于基线模型的平均性能。特别值得注意的是，我们的70B DPO模型在4/6推理任务中获得了最佳分数，其表现优于基线模型及一个141B的最新法律LLM，这证明了我们的知识图谱在增强LLM法律推理能力方面的有效性。