Multimodal vs. Text-Only RAG Architectures: Recall and Reasoning on Cross-Domain Benchmarks

Abstract

Abstract: This report synthesises findings from 14 peer-reviewed papers addressing the following research question: How do multimodal RAG architectures (incorporating text and image retrieval) compare to text-only RAG systems in terms of Recall@1000 and reasoning accuracy on cross-domain benchmarks like JURIS-AQA. Retrieval-Augmented Generation (RAG) has been introduced to mitigate hallucinations in Multimodal Large Language Models (MLLMs) by incorporating external knowledge into the generation process, and it has become a widely adopted approach for knowledge-intensive Visual Question. 14 claims were extracted from source literature; 0 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 2.8/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

How do multimodal RAG architectures (incorporating text and image retrieval) compare to text-only RAG systems in terms of Recall@1000 and reasoning accuracy on cross-domain benchmarks like JURIS-AQA and multimodal QA datasets such as VQA or OK-VQA?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance