arXiv：cs.CL· Ibrahim Siddig, Sviatoslav Tugeev, Munir Georges·· 13 小时前
面向德国法律代码的可验证检索：结构驱动知识图谱如何提升引用准确性
Verifiable Retrieval for Legal Reasoning through Structure-driven Knowledge Graph
AI 导读
针对德国法律代码，研究用结构驱动解析构建知识图谱（KG）来导航和检索源文档，并比较了多种 KG 驱动的分块与检索策略对检索引用准确率的影响。该方法旨在让法律等可靠性关键场景中的 LLM 系统更透明可验证，缓解 RAG 在源数量与规模增大时忽略关键上下文的问题。
正文
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