LegalBenchRAG CUAD: Contract Retrieval Benchmark for Legal Evidence Search

A benchmark dataset for evaluating retrieval-augmented generation systems in the legal domain. It is designed for evidence search tasks involving contracts. The dataset's creator, size, and last update date are unknown.

Use Cases

• Benchmarking legal RAG system performance based on contract retrieval tasks.
• Training models for legal evidence search based on contract content.
• Evaluating the accuracy of information retrieval from legal documents.

Strengths

• Designed specifically for the legal domain, focusing on contract documents.
• Created as a benchmark for a defined task (RAG evidence search).

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.