EcoRAG: A Multi-hop Economic QA Benchmark for Retrieval Augmented Generation Using Knowledge Graphs

Hanieh Khorashadizadeh, Sanju Tiwari, Farah Benamara, Nandana Mihindukulasooriya, Jinghua Groppe, Soror Sahri, Morteza Kamaladdini Ezzabady, Frédéric Ieng, Sven Groppe

Abstract: Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating external knowledge retrieval. However, existing multi-hop RAG benchmarks are limited by shallow reasoning depth, simple retrieval structures, and non-descriptive answers. We introduce EcoRAG, a novel multi-hop economic QA benchmark built on knowledge graphs (KGs). EcoRAG extends retrieval depth to seven-hop reasoning, incorporates complex subgraph structures, and leverages domain-specific economic knowledge. It enables a more realistic evaluation of retrieval and reasoning by bridging the gap between structured knowledge sources and generative models, while also providing a reusable benchmark to advance multi-hop RAG research.