IRB: Automated Generation of Robust Factuality Benchmarks

Static benchmarks for RAG systems often suffer from rapid saturation and require significant manual effort to maintain robustness. To address this, we present IRB, a framework for automatically generating benchmarks to evaluate the factuality of RAG systems. IRB employs a structured generation pipeline utilizing $\mathit{\text{factual}}\mathit{\text{scaffold}}$ and $\mathit{\text{algorithmic}}\mathit{\text{scaffold}}$. We utilize IRB to construct a benchmark and evaluate frontier LLMs and retrievers. Our results demonstrate that IRB poses a significant challenge for frontier LLMs in the closed-book setting. Furthermore, our evaluation suggests that reasoning LLMs are more reliable, and that improving the retrieval component may yield more cost-effective gains in RAG system correctness than scaling the generator.