Verifiable Retrieval for Legal Reasoning through Structure-driven Knowledge Graph

Key points

• Any automation within reliability-critical contexts such as medicine or law has to be transparent and verifiable.1
• 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.1
• However, as the number and size of potential sources increases, naive retrieval approaches tend to perform worse, ignoring critical context elements.1
• In this paper we aim to tackle this problem in the context of German Legal Code.1

Sources (1)

• [1]Verifiable Retrieval for Legal Reasoning through Structure-driven Knowledge Graph
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 9, 02:56 PM

  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.

  Any automation within reliability-critical contexts such as medicine or law has to be transparent and verifiable.

Extractive summary: sentences quoted from the sources.