Multi-modal Retrieval Augmented Multi-modal Generation: Datasets, Evaluation Metrics and Strong Baselines

• URL: http://arxiv.org/abs/2411.16365v3
• Date: Tue, 18 Feb 2025 02:24:32 GMT
• Title: Multi-modal Retrieval Augmented Multi-modal Generation: Datasets, Evaluation Metrics and Strong Baselines
• Authors: Zi-Ao Ma, Tian Lan, Rong-Cheng Tu, Yong Hu, Yu-Shi Zhu, Tong Zhang, Heyan Huang, Xian-Ling Mao,
• Abstract summary: Multi-modal Retrieval Augmented Multi-modal Generation (M$2$RAG) is a novel task that enables foundation models to process multi-modal web content. Despite its potential impact, M$2$RAG remains understudied, lacking comprehensive analysis and high-quality data resources.
• Score: 64.61315565501681
• License:
• Abstract: 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 effectively and construct a training set by filtering high-quality samples using 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 state-of-the-art GPT-4o model. 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.

Related papers

• Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation [2.549112678136113]
  Retrieval-Augmented Generation (RAG) mitigates issues by integrating external dynamic information enhancing factual and updated grounding. Cross-modal alignment and reasoning introduce unique challenges to Multimodal RAG, distinguishing it from traditional unimodal RAG. This survey lays the foundation for developing more capable and reliable AI systems.
  arXiv  Detail & Related papers  (2025-02-12T22:33:41Z)
• Empowering Large Language Models in Wireless Communication: A Novel Dataset and Fine-Tuning Framework [81.29965270493238]
  We develop a specialized dataset aimed at enhancing the evaluation and fine-tuning of large language models (LLMs) for wireless communication applications. The dataset includes a diverse set of multi-hop questions, including true/false and multiple-choice types, spanning varying difficulty levels from easy to hard. We introduce a Pointwise V-Information (PVI) based fine-tuning method, providing a detailed theoretical analysis and justification for its use in quantifying the information content of training data.
  arXiv  Detail & Related papers  (2025-01-16T16:19:53Z)
• GME: Improving Universal Multimodal Retrieval by Multimodal LLMs [43.457928045291915]
  Universal Multimodal Retrieval (UMR) aims to enable search across various modalities using a unified model. Previous work has attempted to adopt multimodal large language models (MLLMs) to realize UMR using only text data.
  arXiv  Detail & Related papers  (2024-12-22T04:40:24Z)
• MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct [148.39859547619156]
  We propose MMEvol, a novel multimodal instruction data evolution framework. MMEvol iteratively improves data quality through a refined combination of fine-grained perception, cognitive reasoning, and interaction evolution. Our approach reaches state-of-the-art (SOTA) performance in nine tasks using significantly less data compared to state-of-the-art models.
  arXiv  Detail & Related papers  (2024-09-09T17:44:00Z)
• What are the Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets? Insights and Best Practices [91.71951459594074]
  Long language models (LLMs) with extended context windows have significantly improved tasks such as information extraction, question answering, and complex planning scenarios. Existing methods typically utilize the Self-Instruct framework to generate instruction tuning data for better long context capability improvement. We propose the Multi-agent Interactive Multi-hop Generation framework, incorporating a Quality Verification Agent, a Single-hop Question Generation Agent, a Multiple Question Sampling Strategy, and a Multi-hop Question Merger Agent. Our findings show that our synthetic high-quality long-context instruction data significantly enhances model performance, even surpassing models trained on larger amounts of human
  arXiv  Detail & Related papers  (2024-09-03T13:30:00Z)
• PIN: A Knowledge-Intensive Dataset for Paired and Interleaved Multimodal Documents [58.35492519636351]
  PIN format is built on three foundational principles: knowledge intensity, scalability, and support for diverse training modalities. We present PIN-14M, an open-source dataset comprising 14 million samples derived from a diverse range of Chinese and English sources.
  arXiv  Detail & Related papers  (2024-06-20T01:43:08Z)
• MM-BigBench: Evaluating Multimodal Models on Multimodal Content Comprehension Tasks [56.60050181186531]
  We introduce MM-BigBench, which incorporates a diverse range of metrics to offer an extensive evaluation of the performance of various models and instructions. Our paper evaluates a total of 20 language models (14 MLLMs) on 14 multimodal datasets spanning 6 tasks, with 10 instructions for each task, and derives novel insights.
  arXiv  Detail & Related papers  (2023-10-13T11:57:04Z)
• Multi-document Summarization: A Comparative Evaluation [0.0]
  This paper is aimed at evaluating state-of-the-art models for Multi-document Summarization (MDS) on different types of datasets in various domains. We analyzed the performance of PRIMERA and PEG models on Big-Survey and MS$2$ datasets.
  arXiv  Detail & Related papers  (2023-09-10T07:43:42Z)
• MELINDA: A Multimodal Dataset for Biomedical Experiment Method Classification [14.820951153262685]
  We introduce a new dataset, MELINDA, for Multimodal biomEdicaL experImeNt methoD clAssification. The dataset is collected in a fully automated distant supervision manner, where the labels are obtained from an existing curated database. We benchmark various state-of-the-art NLP and computer vision models, including unimodal models which only take either caption texts or images as inputs.
  arXiv  Detail & Related papers  (2020-12-16T19:11:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.