Comparison of Text-Based and Image-Based Retrieval in Multimodal Retrieval Augmented Generation Large Language Model Systems
By: Elias Lumer , Alex Cardenas , Matt Melich and more
Potential Business Impact:
Lets computers understand pictures in reports.
Recent advancements in Retrieval-Augmented Generation (RAG) have enabled Large Language Models (LLMs) to access multimodal knowledge bases containing both text and visual information such as charts, diagrams, and tables in financial documents. However, existing multimodal RAG systems rely on LLM-based summarization to convert images into text during preprocessing, storing only text representations in vector databases, which causes loss of contextual information and visual details critical for downstream retrieval and question answering. To address this limitation, we present a comprehensive comparative analysis of two retrieval approaches for multimodal RAG systems, including text-based chunk retrieval (where images are summarized into text before embedding) and direct multimodal embedding retrieval (where images are stored natively in the vector space). We evaluate all three approaches across 6 LLM models and a two multi-modal embedding models on a newly created financial earnings call benchmark comprising 40 question-answer pairs, each paired with 2 documents (1 image and 1 text chunk). Experimental results demonstrate that direct multimodal embedding retrieval significantly outperforms LLM-summary-based approaches, achieving absolute improvements of 13% in mean average precision (mAP@5) and 11% in normalized discounted cumulative gain. These gains correspond to relative improvements of 32% in mAP@5 and 20% in nDCG@5, providing stronger evidence of their practical impact. We additionally find that direct multimodal retrieval produces more accurate and factually consistent answers as measured by LLM-as-a-judge pairwise comparisons. We demonstrate that LLM summarization introduces information loss during preprocessing, whereas direct multimodal embeddings preserve visual context for retrieval and inference.
Similar Papers
Comparison of Text-Based and Image-Based Retrieval in Multimodal Retrieval Augmented Generation Large Language Model Systems
Computation and Language
Lets computers understand pictures in reports.
Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding
Computation and Language
Helps computers understand all parts of documents.
Multimodal RAG Enhanced Visual Description
Machine Learning (CS)
Helps computers describe pictures better and faster.