Legal RAG Bench: an end-to-end benchmark for legal RAG
We introduce Legal RAG Bench, a benchmark and evaluation methodology for assessing the end-to-end performance of legal RAG systems. As a benchmark, Legal RAG Bench consists of 4,876 passages from the Victorian Criminal Charge Book alongside 100 complex, hand-crafted questions demanding expert knowledge of criminal law and procedure. Both long-form answers and supporting passages are provided. As an evaluation methodology, Legal RAG Bench leverages a full factorial design and novel hierarchical error decomposition framework, enabling apples-to-apples comparisons of the contributions of retrieval and reasoning models in RAG. We evaluate three state-of-the-art embedding models (Isaacus' Kano...
| Authors | Abdur-Rahman Butler, Umar Butler |
|---|---|
| Primary category | cs.CL |
| Published | 2 March 2026 |
| Last updated at source | 2 March 2026 |
Connected in the knowledge graph
- AccountVerify/swiss-caselawDataset · cited by
- isaacus/legal-rag-benchDataset · cited by
- voilaj/swiss-caselawDataset · cited by
Models and datasets referencing this paper
- voilaj/swiss-caselawDataset
- isaacus/legal-rag-benchDataset
- AccountVerify/swiss-caselawDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.