Evaluation of GraphRAG Strategies for Efficient Information Retrieval

Retrieval Augmented Generation (RAG) has emerged as a solution to enhance large language models (LLMs) and avoid hallucination by grounding their answers in external data. However, traditional RAG systems struggle to capture relationships and cross-references between different sources unless explicitly mentioned. This challenge is common in real-world scenarios, where information is often distributed and interlinked, making graphs a more effective representation. Recent research has focused on using GraphRAG systems that retrieve subgraphs instead of isolated passages, improving both interpretability and retrieval precision. Our work provides a technical contribution through a comparative evaluation of retrieval strategies within GraphRAG, focusing on context relevance rather than abstract metrics. We aim to offer practitioners actionable insights into the retrieval component of the GraphRAG pipeline. We experimented with a biochemical knowledge graph, benchmarking four graph-based retrieval strategies. To assess retrieval quality, we developed a refined framework inspired by ARES, minimizing the reliance on reference-based evaluations.

Asma Houimli, Zaineb Gabsi, Sabri Skhiri, Evaluation of GraphRAG Strategies for Efficient Information Retrieval, In Proc. of the 5th Workshop on Knowledge Graphs and Big Data, IEEE Big Data, December 2025.

Click here to access the paper.