Generative Multi-Modal Knowledge Retrieval with Large Language Models

TL;DR

This paper introduces an end-to-end generative framework leveraging large language models for multi-modal knowledge retrieval, improving effectiveness and training efficiency in handling multi-modal queries.

Contribution

It proposes a novel approach combining object-aware prefix-tuning and knowledge-guided generation to enhance multi-modal knowledge retrieval with LLMs.

Findings

Achieved 3.0% to 14.6% improvements on three benchmarks.

Effectively aligns multi-grained visual features into textual space.

Demonstrates the effectiveness of the proposed framework over strong baselines.

Abstract

Knowledge retrieval with multi-modal queries plays a crucial role in supporting knowledge-intensive multi-modal applications. However, existing methods face challenges in terms of their effectiveness and training efficiency, especially when it comes to training and integrating multiple retrievers to handle multi-modal queries. In this paper, we propose an innovative end-to-end generative framework for multi-modal knowledge retrieval. Our framework takes advantage of the fact that large language models (LLMs) can effectively serve as virtual knowledge bases, even when trained with limited data. We retrieve knowledge via a two-step process: 1) generating knowledge clues related to the queries, and 2) obtaining the relevant document by searching databases using the knowledge clue. In particular, we first introduce an object-aware prefix-tuning technique to guide multi-grained visual learning. Then, we align multi-grained visual features into the textual feature space of the LLM, employing the LLM to capture cross-modal interactions. Subsequently, we construct instruction data with a unified format for model training. Finally, we propose the knowledge-guided generation strategy to impose prior constraints in the decoding steps, thereby promoting the generation of distinctive knowledge clues. Through experiments conducted on three benchmarks, we demonstrate significant improvements ranging from 3.0% to 14.6% across all evaluation metrics when compared to strong baselines.