FinRAGBench-V

'FinRAGBench-V' is a benchmark dataset used to evaluate multimodal retrieval-augmented generation systems, particularly in the context of enterprise question-and-answer tasks involving complex documents.

Papers using FinRAGBench-V (3)

MM-BizRAG: Rethinking Multimodal Retrieval-Augmented Generation for General Purpose Enterprise Q&A2026Finragbench-v: A Benchmark For Multimodal RAG With Visual Citation In The Financial Domain2025 · 2 citesDocLens : A Tool-Augmented Multi-Agent Framework for Long Visual Document Understanding2025