用法律条文增强大模型，让非中文国家法律问答更准确可信
GAIus: Combining Genai with Legal Clauses Retrieval for Knowledge-based Assistant
- 基于波兰民法典构建可解释的法律条文检索机制
- 使GPT-3.5推理能力提升419%，超越GPT-4o
- 适合法律AI助手研发者与跨语言法律技术研究者
本文探讨大语言模型在处理非英语、非中文国家法律问题时，如何基于可靠法律条文生成答案并提供引用。文章回顾了法律信息检索的发展历程，分析判例法与成文法的差异及其对法律任务的影响，并综述该领域最新研究进展。在此基础上，提出gAIus——一种基于认知架构的LLM法律代理系统，其回答依赖于从波兰民法典中检索的知识。我们设计了一种更具可解释性、更友好的检索机制，优于传统的嵌入式方法。为评估效果，我们构建了一个基于波兰法律实习入学考试单选题的专用数据集。实验表明，该架构显著提升GPT-3.5-turbo-0125性能（提升419%），使其超过GPT-4o；同时将GPT-4o-mini得分从31%提升至86%。论文最后展望了未来研究方向及潜在应用。
原文摘要 · Abstract (English)
In this paper we discuss the capability of large language models to base their answer and provide proper references when dealing with legal matters of non-english and non-chinese speaking country. We discuss the history of legal information retrieval, the difference between case law and statute law, its impact on the legal tasks and analyze the latest research in this field. Basing on that background we introduce gAIus, the architecture of the cognitive LLM-based agent, whose responses are based on the knowledge retrieved from certain legal act, which is Polish Civil Code. We propose a retrieval mechanism which is more explainable, human-friendly and achieves better results than embedding-based approaches. To evaluate our method we create special dataset based on single-choice questions from entrance exams for law apprenticeships conducted in Poland. The proposed architecture critically leveraged the abilities of used large language models, improving the gpt-3.5-turbo-0125 by 419%, allowing it to beat gpt-4o and lifting gpt-4o-mini score from 31% to 86%. At the end of our paper we show the possible future path of research and potential applications of our findings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。