Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ma, Zi-Ao, Lan, Tian, Tu, Rong-Cheng, Hu, Yong, Zhu, Yu-Shi, Zhang, Tong, Huang, Heyan, Wu, Zhijing, Mao, Xian-Ling
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2411.16365
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912388649844736
author Ma, Zi-Ao
Lan, Tian
Tu, Rong-Cheng
Hu, Yong
Zhu, Yu-Shi
Zhang, Tong
Huang, Heyan
Wu, Zhijing
Mao, Xian-Ling
author_facet Ma, Zi-Ao
Lan, Tian
Tu, Rong-Cheng
Hu, Yong
Zhu, Yu-Shi
Zhang, Tong
Huang, Heyan
Wu, Zhijing
Mao, Xian-Ling
contents We present a systematic investigation of Multi-modal Retrieval Augmented Multi-modal Generation (M$^2$RAG), a novel task that enables foundation models to process multi-modal web content and generate multi-modal responses, which exhibits better information density and readability. Despite its potential impact, M$^2$RAG remains understudied, lacking comprehensive analysis and high-quality data resources. To address this gap, we establish a comprehensive benchmark through a rigorous data curation pipeline, and employ text-modal metrics and multi-modal metrics based on foundation models for evaluation. We further propose several strategies for foundation models to process M$^2$RAG task effectively and construct a training set by filtering high-quality samples using our designed metrics. Our extensive experiments demonstrate the reliability of our proposed metrics, a landscape of model performance within our designed strategies, and show that our fine-tuned 7B-8B models outperform the GPT-4o model and approach the state-of-the-art OpenAI o3-mini. Additionally, we perform fine-grained analyses across diverse domains and validate the effectiveness of our designs in data curation pipeline. All resources, including codes, datasets, and model weights, will be publicly released.
format Preprint
id arxiv_https___arxiv_org_abs_2411_16365
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-modal Retrieval Augmented Multi-modal Generation: Datasets, Evaluation Metrics and Strong Baselines
Ma, Zi-Ao
Lan, Tian
Tu, Rong-Cheng
Hu, Yong
Zhu, Yu-Shi
Zhang, Tong
Huang, Heyan
Wu, Zhijing
Mao, Xian-Ling
Computation and Language
We present a systematic investigation of Multi-modal Retrieval Augmented Multi-modal Generation (M$^2$RAG), a novel task that enables foundation models to process multi-modal web content and generate multi-modal responses, which exhibits better information density and readability. Despite its potential impact, M$^2$RAG remains understudied, lacking comprehensive analysis and high-quality data resources. To address this gap, we establish a comprehensive benchmark through a rigorous data curation pipeline, and employ text-modal metrics and multi-modal metrics based on foundation models for evaluation. We further propose several strategies for foundation models to process M$^2$RAG task effectively and construct a training set by filtering high-quality samples using our designed metrics. Our extensive experiments demonstrate the reliability of our proposed metrics, a landscape of model performance within our designed strategies, and show that our fine-tuned 7B-8B models outperform the GPT-4o model and approach the state-of-the-art OpenAI o3-mini. Additionally, we perform fine-grained analyses across diverse domains and validate the effectiveness of our designs in data curation pipeline. All resources, including codes, datasets, and model weights, will be publicly released.
title Multi-modal Retrieval Augmented Multi-modal Generation: Datasets, Evaluation Metrics and Strong Baselines
topic Computation and Language
url https://arxiv.org/abs/2411.16365