Multimodal Sentiment Analysis (MSA) leverages multiple data modals to analyze human sentiment. Existing MSA models generally employ cutting-edge multimodal fusion and representation learning-based methods to promote MSA capability. However, there are two key challenges: (i) in existing multimodal fusion methods, the decoupling of modal combinations and tremendous parameter redundancy, lead to insufficient fusion performance and efficiency; (ii) a challenging trade-off exists between representation capability and computational overhead in unimodal feature extractors and encoders. Our proposed GResearch goal: What is the computational overhead and latency trade-off of graph-based fusion methods versus token redundancy reduction techniques in cross-document NLI tasks?Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.5/10.