arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.02665cs.CL
收藏

多模态大语言模型中的自我改进:综述

Self-Improvement in Multimodal Large Language Models: A Survey

The University of Texas at Dallas(德克萨斯大学达拉斯分校);University of Toronto(多伦多大学);University of Notre Dame(诺特丹大学);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)

Shijian Deng, Kai Wang, Tianyu Yang, Harsh Singh, Yapeng Tian

AI总结:

该综述首次系统梳理多模态大语言模型(MLLMs)的自我改进技术,从数据收集、组织、优化三维度分类现有方法,介绍评估与下游应用,指出挑战与未来方向,助力该领域发展。

摘要:

大语言模型(LLMs)自我改进领域的最新进展在不显著增加成本(尤其是人力成本)的前提下,有效提升了模型能力。尽管该领域仍处于相对早期阶段,将其拓展至多模态领域在利用多元数据源、开发更通用的自我改进模型方面具备巨大潜力。本综述是首份针对多模态大语言模型(MLLMs)中自我改进技术的全面概述。我们对现有文献进行了结构化梳理,并从三个维度探讨相关方法:1)数据收集,2)数据组织,3)模型优化,以推动MLLMs自我改进技术的进一步发展。我们还纳入了常用的评估方法与下游应用。最后,我们总结了现存的开放性挑战与未来研究方向。

英文摘要:

Recent advancements in self-improvement for Large Language Models (LLMs) have efficiently enhanced model capabilities without significantly increasing costs, particularly in terms of human effort. While this area is still relatively young, its extension to the multimodal domain holds immense potential for leveraging diverse data sources and developing more general self-improving models. This survey is the first to provide a comprehensive overview of self-improvement in Multimodal LLMs (MLLMs). We provide a structured overview of the current literature and discuss methods from three perspectives: 1) data collection, 2) data organization, and 3) model optimization, to facilitate the further development of self-improvement in MLLMs. We also include commonly used evaluations and downstream applications. Finally, we conclude by outlining open challenges and future research directions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑