Single-vector aggregation in visual financial document retrieval collapses semantically distinct documents due to global texture dominance, as demonstrated by a new diagnostic benchmark where patch-level signals detect changes that aggregated vectors obscure.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
MimirRAG, a multi-agent RAG framework with metadata integration and table-aware chunking, reaches 89.3% accuracy on FinanceBench and outperforms prior baselines for financial document retrieval.
citing papers explorer
-
A Picture is Worth a Thousand Words? An Empirical Study of Aggregation Strategies for Visual Financial Document Retrieval
Single-vector aggregation in visual financial document retrieval collapses semantically distinct documents due to global texture dominance, as demonstrated by a new diagnostic benchmark where patch-level signals detect changes that aggregated vectors obscure.
-
MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integration
MimirRAG, a multi-agent RAG framework with metadata integration and table-aware chunking, reaches 89.3% accuracy on FinanceBench and outperforms prior baselines for financial document retrieval.