Gold Reference Set for Evaluating Retrieval-Augmented Generation Systems in Tobacco Research

This dataset contains a rigorously developed and validated gold reference set of 20 query-response pairs used to evaluate Retrieval-Augmented Generation (RAG) systems in the domain of tobacco research. The queries and responses were derived from the PMI Integrated Report 2023 and were iteratively reviewed and refined by tobacco research domain specialists to ensure accuracy, relevance, and domain specificity.