MIRAGE is a lightweight RAG evaluation benchmark with 7,560 QA pairs and four error-type metrics that partition outcomes across base, oracle, and mixed contexts.
However, annotators were instructed that the presence of an answer span does not directly indicate relevance
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MIRAGE: A Metric-Intensive Benchmark for Retrieval-Augmented Generation Evaluation
MIRAGE is a lightweight RAG evaluation benchmark with 7,560 QA pairs and four error-type metrics that partition outcomes across base, oracle, and mixed contexts.