Overcoming the "Impracticality" of RAG: Proposing a Real-World Benchmark and Multi-Dimensional Diagnostic Framework

TL;DR

This paper introduces a multi-dimensional diagnostic framework and an enterprise RAG benchmark to better evaluate and diagnose the complex challenges faced in real-world deployment beyond simple accuracy.

Contribution

It proposes a novel four-axis difficulty taxonomy and integrates it into a benchmark to systematically diagnose RAG system weaknesses in enterprise settings.

Findings

Existing benchmarks do not diagnose multi-faceted challenges.

The framework reveals specific weaknesses in RAG systems.

The benchmark aids in aligning model performance with operational needs.

Abstract

Performance evaluation of Retrieval-Augmented Generation (RAG) systems within enterprise environments is governed by multi-dimensional and composite factors extending far beyond simple final accuracy checks. These factors include reasoning complexity, retrieval difficulty, the diverse structure of documents, and stringent requirements for operational explainability. Existing academic benchmarks fail to systematically diagnose these interlocking challenges, resulting in a critical gap where models achieving high performance scores fail to meet the expected reliability in practical deployment. To bridge this discrepancy, this research proposes a multi-dimensional diagnostic framework by defining a four-axis difficulty taxonomy and integrating it into an enterprise RAG benchmark to diagnose potential system weaknesses.