arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.19341cs.CV
收藏

MMKG-R1:通过强化学习构建多模态知识图谱

MMKG-R1: Constructing Multimodal Knowledge Graphs via Reinforcement Learning

The Pennsylvania State University(宾夕法尼亚州立大学)

Zongyu Wu, Yilong Wang, Xiaochen Wang, Minhua Lin, Yuan Zhong, Fenglong Ma, Xiang Zhang, Suhang Wang

AI总结:

该研究针对现有多模态知识图谱构建方法缺乏质量指导的问题,提出MMKG-R1框架,引入感知质量的奖励指导强化学习训练,构建的MMKG可提升下游问答准确率。

摘要:

多模态知识图谱(MMKGs)整合不同模态的信息以支撑多模态图检索增强生成(Graph RAG),其目标是提升多模态大语言模型(MLLMs)的性能。这类多模态图RAG方法的有效性在很大程度上依赖于所构建MMKGs的质量。然而,现有大多数方法构建MMKGs时未对图质量提供明确指导,而依赖最终答案正确性的强化学习(RL)方法可能仅能提供关于MMKG质量的间接反馈。为解决这些局限,本文提出MMKG-R1,一种新颖的、以MMKG质量为驱动的RL框架,用于将MLLM训练为多模态知识构建器。具体而言,MMKG-R1引入多种感知质量的奖励,以直接评估从单个知识源提取的信息质量以及组装后的MMKG的质量,随后利用这些奖励指导RL训练。在多个数据集上开展的实验表明,MMKG-R1构建的MMKG可提升下游问答任务的准确率。

英文摘要:

Multimodal knowledge graphs (MMKGs) organize information across different modalities to support multimodal Graph Retrieval-Augmented Generation (RAG), which aims to improve the performance of multimodal large language models (MLLMs). The effectiveness of these multimodal Graph RAG methods largely depends on the quality of the constructed MMKGs. However, most existing methods construct MMKGs without explicit guidance on graph quality, while reinforcement learning (RL)-based methods that rely on final-answer correctness may provide only indirect feedback on MMKG quality. To address these limitations, we propose MMKG-R1, a novel MMKG-quality-driven RL framework for training an MLLM as a multimodal knowledge constructor. To be specific, MMKG-R1 introduces multiple quality-aware rewards to directly evaluate both the quality of information extracted from individual knowledge sources and the quality of the assembled MMKG. These rewards are then used to guide the RL training. Experiments across multiple datasets show that MMKG-R1 constructs MMKGs that improve downstream question-answering accuracy.

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。

↑