CogniVerse：以认知反思与几何推理革新多模态检索增强生成
CogniVerse: Revolutionizing Multi-Modal Retrieval-Augmented Generation with Cognitive Reflection and Geometric Reasoning
为视觉语言模型的知识密集型问答提供了一种基于黎曼流形对齐和谱图优化的多模态检索增强生成框架，其认知反思模块可动态判断检索必要性，对构建高效可靠的视觉问答系统有直接参考价值。
原文依据 Multi-modal Retrieval-Augmented Generation (MMRAG) has emerged as a powerful paradigm for enhancing Multimodal Large Language Models (MLLMs) in knowledge-intensive question answering
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论多模态检索增强生成（MMRAG）已成为一种强大的范式，通过整合外部视觉、文本和结构化知识来增强多模态大语言模型（MLLMs）在知识密集型问答中的能力。然而，现有的MMRAG框架存在关键局限性，包括检索噪声大且不相关、跨模态语义不对齐、缺乏自适应推理以及局部与全局上下文生成不连贯。我们提出CogniVerse，一种新颖的MMRAG框架，通过受认知启发的、数学严谨的方法应对这些挑战。CogniVerse借鉴类人推理，集成了三个协同组件：（1）认知反思模块（CRM），动态评估检索必要性并过滤相关的多模态内容，减少噪声和计算开销；（2）多模态检索模块，利用信息几何在黎曼流形中对齐嵌入，并通过谱图理论精炼知识图谱，确保精确且连贯的检索；（3）分层生成模块，采用基于最优传输的损失来平衡词元级准确性和全局语义连贯性。CogniVerse植根于先进的理论框架，包括几何对齐和谱优化的收敛保证，实现了鲁棒的跨模态集成和自适应知识利用。大量实验表明，CogniVerse在准确性和连贯性上显著优于最优系统，同时降低了检索延迟。
英文原文摘要 1625 字符
Multi-modal Retrieval-Augmented Generation (MMRAG) has emerged as a powerful paradigm for enhancing Multimodal Large Language Models (MLLMs) in knowledge-intensive question answering by integrating external visual, textual, and structural knowledge. However, existing MMRAG frameworks suffer from critical limitations, including noisy and irrelevant retrieval, cross-modal semantic misalignment, lack of adaptive reasoning, and incoherent generation across local and global contexts. We introduce CogniVerse, a novel MMRAG framework that addresses these challenges through a cognitive-inspired, mathematically rigorous approach. Drawing from human-like reasoning, CogniVerse integrates three synergistic components: (1) a Cognitive Reflection Module (CRM) that dynamically assesses retrieval necessity and filters relevant multi-modal content, reducing noise and computational overhead; (2) a Multi-modal Retrieval Module that aligns embeddings in a Riemannian manifold using information geometry and refines knowledge graphs via spectral graph theory, ensuring precise and coherent retrieval; and (3) a Hierarchical Generation Module that employs an optimal transport-based loss to balance token-level accuracy and global semantic coherence. Grounded in advanced theoretical frameworks, including convergence guarantees for geometric alignment and spectral optimization, CogniVerse achieves robust cross-modal integration and adaptive knowledge utilization. Extensive experiments demonstrate that CogniVerse significantly outperforms state-of-the-art systems in both accuracy and coherence, while reducing retrieval latency.