UniRAG: Universal Retrieval Augmentation for Large Vision Language Models
Sahel Sharifymoghaddam, Shivani R Upadhyay, Wenhu Chen, Jimmy Lin · 2025
Recently, Large Vision Language Models (LVLMs) have unlocked many complex use cases that require Multi-Modal (MM) understanding (e.g., image captioning or visual question answering) and MM generation (e.g., textguided image generation or editing) capabilities.To further improve the output fidelity of LVLMs we introduce UniRAG, a plug-andplay technique that adds relevant retrieved information to prompts as few-shot examples during inference.Unlike the common belief that Retrieval Augmentation (RA) mainly improves generation or understanding of uncommon entities, our evaluation results on the MSCOCO dataset with common entities show that both proprietary models like GPT-4o and Gemini-Pro and smaller open-source models like LLaVA, LaVIT, and Emu2 significantly enhance their generation quality when their input prompts are augmented with relevant information retrieved by Vision-Language (VL) retrievers like UniIR models.All the necessary code to reproduce our results is available at https://github.com/castorini/UniRAG