RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering

TL;DR

This paper introduces RAG-IGBench, a comprehensive benchmark for evaluating interleaved image-text generation in open-domain question answering, addressing the lack of specialized metrics and datasets for multimodal content quality assessment.

Contribution

We present RAG-IGBench, a novel benchmark with innovative evaluation metrics and a diverse dataset, enabling better assessment of multimodal models in open-domain QA tasks.

Findings

State-of-the-art models show room for improvement in multimodal coherence.

Our metrics correlate highly with human judgments.

Fine-tuned models outperform baseline on RAG-IGBench.

Abstract

In real-world scenarios, providing user queries with visually enhanced responses can considerably benefit understanding and memory, underscoring the great value of interleaved image-text generation. Despite recent progress, like the visual autoregressive model that unifies text and image processing in a single transformer architecture, generating high-quality interleaved content remains challenging. Moreover, evaluations of these interleaved sequences largely remain underexplored, with existing benchmarks often limited by unimodal metrics that inadequately assess the intricacies of combined image-text outputs. To address these issues, we present RAG-IGBench, a thorough benchmark designed specifically to evaluate the task of Interleaved Generation based on Retrieval-Augmented Generation (RAG-IG) in open-domain question answering. RAG-IG integrates multimodal large language models (MLLMs) with retrieval mechanisms, enabling the models to access external image-text information for generating coherent multimodal content. Distinct from previous datasets, RAG-IGBench draws on the latest publicly available content from social platforms and introduces innovative evaluation metrics that measure the quality of text and images, as well as their consistency. Through extensive experiments with state-of-the-art MLLMs (both open-source and proprietary) on RAG-IGBench, we provide an in-depth analysis examining the capabilities and limitations of these models. Additionally, we validate our evaluation metrics by demonstrating their high correlation with human assessments. Models fine-tuned on RAG-IGBench's training set exhibit improved performance across multiple benchmarks, confirming both the quality and practical utility of our dataset. Our benchmark is available at https://github.com/USTC-StarTeam/RAG-IGBench.