Multi-Modal Generative Fuzzy System: Fuzzy Inference Guided Large Model Interactive Question Answering Framework
Summary
This paper proposes a Multi-Modal Generative Fuzzy System (MMGFS) to enhance multimodal question answering by addressing modality bias and uncertainty through fuzzy inference and multi-hop reasoning, demonstrating improved performance on multiple benchmarks.
View Cached Full Text
Cached at: 08/18/26, 09:43 AM
# Multi-Modal Generative Fuzzy System: Fuzzy Inference Guided Large Model Interactive Question Answering Framework Source: [https://arxiv.org/abs/2608.14584](https://arxiv.org/abs/2608.14584) [View PDF](https://arxiv.org/pdf/2608.14584) > Abstract:In Multimodal Question Answering \(MQA\), models are required to jointly encode and integrate heterogeneous information from multiple modalities, including text, images, and speech, to perform complex semantic reasoning and decision making\. Despite recent advances, existing approaches, including traditional deep learning models and Large Models \(LMs\) or prompt\-based frameworks, continue to face several critical challenges\. First, modality bias arises from discrepancies in feature distributions across different modalities, which limits effective cross modal collaborative understanding\. Second, many questions require knowledge drawn from multiple domains, introducing significant uncertainty\. Third, current methods often rely on shallow semantic matching, resulting in limited reasoning depth an reduced interpretability\. To address these issues, inspired by the traditional fuzzy system \(FS\) framework, we propose a fuzzy\-inference\-guided multimodal generative architecture termed the Multi\-Modal Generative Fuzzy System \(MMGFS\)\. The main contributions of MMGFS are two folds\. First, it alleviates modality bias through a multimodal collaborative rumination mechanism\. Second, it introduces fuzzy rules and a multi\-hop inference mechanism to support cross\-domain knowledge fusion and hierarchical reasoning, thereby strengthening uncertainty modelling and deepening semantic understanding\. We conduct comprehensive evaluations on open\-domain question answering datasets, including MultimodalQA and WebQA, as well as domain\-specific benchmarks, including BioMol\-VQA and EHRxQA\. Experimental results demonstrate that MMGFS consistently outperforms existing methods across multiple datasets\. It effectively mitigates modality bias and question uncertainty while achieving superior performance in answer accuracy, consistency, and generalization\. ## Submission history From: Hailong Yang \[[view email](https://arxiv.org/show-email/715bbb5a/2608.14584)\] **\[v1\]**Wed, 17 Jun 2026 01:22:27 UTC \(1,199 KB\)
Similar Articles
MM-BizRAG: Rethinking Multimodal Retrieval-Augmented Generation for General Purpose Enterprise Q&A
MM-BizRAG is a multimodal retrieval-augmented generation system for enterprise Q&A that uses document structure-aware splitting and layout-aware parsing to outperform vision-centric baselines by up to 32% on heterogeneous enterprise documents. The paper also introduces FastRAGEval, a cost-efficient LLM-based evaluation metric with stronger human alignment than RAGChecker.
Towards Robust Federated Multimodal Graph Learning under Modality Heterogeneity
This paper proposes FedMPO, a robust federated multimodal graph learning method that addresses modality heterogeneity and missing modalities through topology-aware cross-modal generation, missing-aware expert routing, and reliability-aware aggregation, achieving performance gains on multiple datasets.
RSF-GLLM: Bridging the Semantic Gap in Multi-Hop Knowledge Graph QA via Recurrent Soft-Flow and Decoupled LLM Generation
This paper introduces RSF-GLLM, a framework that decouples differentiable graph reasoning from LLM generation to address the semantic gap in multi-hop knowledge graph question answering, achieving competitive performance with superior inference efficiency.
D$^2$F-ReAG: Dynamic Decomposition and Filtering for Multi-Hop Reasoning-Augmented Generation
This paper introduces D2F-ReAG, a novel paradigm for multi-hop reasoning-augmented generation that dynamically controls reasoning depth by judging root-level reasoning reliability and decomposing questions into sub-questions when needed, improving accuracy on multi-hop benchmarks.
MODF-SIR: A Multi-agent Omni-modal Distilled Framework for Social Intelligence Reasoning
This paper proposes MODF-SIR, a multi-agent collaborative framework built on a lightweight multimodal large language model for social intelligence reasoning. It employs knowledge distillation, long-tail event extraction, and test-time adaptation to achieve state-of-the-art results with reduced training data.