UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities
This addresses the problem of handling real-world queries requiring varied knowledge types for users of multimodal AI systems, representing a novel method for a known bottleneck.
The paper tackles the limitation of existing RAG systems to single-modality corpora by introducing UniversalRAG, a framework that retrieves and integrates knowledge from heterogeneous sources with diverse modalities and granularities, achieving superiority over baselines on 8 benchmarks.
Retrieval-Augmented Generation (RAG) has shown substantial promise in improving factual accuracy by grounding model responses with external knowledge relevant to queries. However, most existing RAG approaches are limited to a text-only corpus, and while recent efforts have extended RAG to other modalities such as images and videos, they typically operate over a single modality-specific corpus. In contrast, real-world queries vary widely in the type of knowledge they require, which a single type of knowledge source cannot address. To address this, we introduce UniversalRAG, a novel RAG framework designed to retrieve and integrate knowledge from heterogeneous sources with diverse modalities and granularities. Specifically, motivated by the observation that forcing all modalities into a unified representation space derived from a single aggregated corpus causes a modality gap, where the retrieval tends to favor items from the same modality as the query, we propose a modality-aware routing mechanism that dynamically identifies the most appropriate modality-specific corpus and performs targeted retrieval within it. Also, beyond modality, we organize each modality into multiple granularity levels, enabling fine-tuned retrieval tailored to the complexity and scope of the query. We validate UniversalRAG on 8 benchmarks spanning multiple modalities, showing its superiority over various modality-specific and unified baselines.