Exécution de notre outil de synthèse sur un nouvel article
Vérifiez l’article ci-dessous, puis lancez sa synthèse.
Automated Testing Framework for Retrieval-Augmented Generation Systems: Evaluation Metrics and Optimization Strategies
Jun Zhang, Rui He, Xiaodong Zheng (China Energy Engineering Corporation (China)), Yang Lin (China Energy Engineering Corporation (China)), Shixiang Lu (China Energy Engineering Corporation (China)), Yeheng Qu (China Energy Engineering Corporation (China))
Résumé : The rapid development of Retrieval-Augmented Generation (RAG) systems has addressed critical limitations in large language models (LLMs), including factual hallucinations, knowledge obsolescence, and domain-specific incompetence. However, the complexity of RAG architectures introduces new challenges in performance evaluation. This paper proposes a comprehensive automated testing framework that systematically assesses both retrieval and generation components through quantifiable metrics. Our experimental results demonstrate that the weighted integration of context recall (CR) and answer correctness (AC) yields 17.1% higher discriminative power than single metrics, while semantic-aware document chunking improves answer relevance by 13.0%. This study not only provides actionable strategies for fine-tuning RAG systems but also codifies standardized benchmark protocols tailored to their industrial deployment.