arXiv cs.CL· Ibrahim Siddig, Sviatoslav Tugeev, Munir Georges·· 6 天前AI 评分22
通过结构驱动知识图谱实现法律推理的可验证检索
Verifiable Retrieval for Legal Reasoning through Structure-driven Knowledge Graph
AI 导读
针对德国法律法典，研究用结构驱动解析构建知识图谱来导航和检索源文档，并对比多种 KG 引导的分块与检索策略对引用准确率的影响。该方法旨在解决 RAG 在源文档数量和规模增大时检索性能下降、忽略关键上下文的问题，从而提升法律等可靠性关键场景中生成过程的可验证性。
正文 · 原文
Abstract:Any automation within reliability-critical contexts such as medicine or law has to be transparent and verifiable. Despite their advantages, current LLM-based systems do not meet these requirements due to their inherent black-box nature. Retrieval Augmented Generation (RAG) attempts to ground the generative process in the relevant interpretable documents, thereby reducing the risk of AI 'hallucinations' and potentially enabling verification of the initial generation context. However, as the number and size of potential sources increases, naive retrieval approaches tend to perform worse, ignoring critical context elements. In this paper we aim to tackle this problem in the context of German Legal Code. Using structure-driven parsing to create a Knowledge Graph (KG) for the source document navigation and retrieval, we compare several KG-informed chunking and retrieval strategies and evaluate their effect on the accuracy of retrieved citations.
| Comments: | Accepted at the RAGE-KG 2026 Workshop, co-located with ISWC 2026. 7 pages, 3 figures |
| Subjects: | Computation and Language (cs.CL) |
| ACM classes: | I.2.7; H.3.3 |
| Cite as: | arXiv:2610.13695 [cs.CL] |
| (or arXiv:2610.13695v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.13695 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ibrahim Siddig [view email]
[v1]
Fri, 9 Oct 2026 14:56:31 UTC (298 KB)
来源：arXiv cs.CL · arxiv.org