Semantic-Aligned Structural Abstraction for Multimodal Sentiment Analysis

arXiv:2607.27790 · cs.CL, cs.AI · Submitted 2026-07-30 · Read on arXiv

Wei Chen, Junkai Li, Tongguan Wang, Hui Liu, Feiyue Xue, Chuanxiang Ma, Ying Sha

cs.CL, cs.AI

Submitted: 2026-07-30

Comments: Accepted by MM 2026

DOI: 10.1145/3767308.3835866

Code: https://github.com/especiallyW/SentiLLM

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Calibration — 23× in this paper · explained in 9 episodes
• Sparsity — 22× in this paper · explained in 5 episodes
• Disentanglement — 21× in this paper · explained in 2 episodes
• Abstraction — 19× in this paper · explained in 1 episode
• Multimodal Sentiment Analysis — 18× in this paper
• Accuracy — 11× in this paper · explained in 1 episode
• Ablation — 7× in this paper · explained in 1 episode
• Transformer — 7× in this paper · explained in 2 episodes
• Ablation Study — 5× in this paper · explained in 3 episodes
• Generalization — 5× in this paper · explained in 14 episodes
• Multimodal Fusion — 4× in this paper · explained in 4 episodes
• Mutual Information — 4× in this paper · explained in 2 episodes
• Distillation — 3× in this paper · explained in 2 episodes
• F1 Score — 3× in this paper · explained in 4 episodes
• Hyperparameters — 3× in this paper · explained in 2 episodes
• Instruction Tuning — 3× in this paper · explained in 3 episodes
• Language Models (LLMs) — 3× in this paper · explained in 2 episodes
• Papers — 3× in this paper · explained in 3 episodes
• Robustness — 3× in this paper · explained in 6 episodes
• Transformers — 3× in this paper · explained in 2 episodes
• Ablation Studies — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Clustering — 2× in this paper · explained in 2 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Core — 2× in this paper · explained in 2 episodes
• Feature Extraction — 2× in this paper · explained in 3 episodes
• Interpretability — 2× in this paper · explained in 15 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 9 episodes
• Mean Absolute Error — 2× in this paper
• Multimodal Inputs — 2× in this paper · explained in 2 episodes
• Multimodal Integration — 2× in this paper · explained in 2 episodes
• Multimodal Learning — 2× in this paper · explained in 2 episodes
• Redundancy — 2× in this paper · explained in 2 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Tensor Fusion Network — 2× in this paper
• Attention Mechanism — 1× in this paper · explained in 3 episodes
• Class Imbalance — 1× in this paper · explained in 3 episodes
• Computational Efficiency — 1× in this paper · explained in 2 episodes
• Contrastive Learning — 1× in this paper · explained in 9 episodes
• Decoupled Multimodal Distillation — 1× in this paper
• Decoupling — 1× in this paper · explained in 2 episodes
• Disentangled-Language-Focused Framework — 1× in this paper
• Embeddings — 1× in this paper · explained in 2 episodes
• Entanglement — 1× in this paper · explained in 5 episodes
• Feed-Forward Network — 1× in this paper
• Few-Shot Learning — 1× in this paper · explained in 6 episodes
• Generalization Capabilities — 1× in this paper · explained in 2 episodes
• Knowledge Distillation — 1× in this paper · explained in 15 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Learning Paradigms — 1× in this paper · explained in 2 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Low-rank Multimodal Fusion — 1× in this paper
• MLLMs — 1× in this paper · explained in 2 episodes
• Modality Gap — 1× in this paper · explained in 6 episodes
• Multimodal Dataset — 1× in this paper · explained in 2 episodes
• Multimodal Mutual Information Maximization — 1× in this paper
• Pseudo-labels — 1× in this paper · explained in 2 episodes
• Representation Learning — 1× in this paper · explained in 3 episodes
• Self-Supervised Learning — 1× in this paper · explained in 8 episodes
• Semantic Gap — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 6 episodes
• Weight Decay — 1× in this paper · explained in 2 episodes

Sources

• Layer Normalization
• InternLM2 Technical Report
• Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis
• UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition
• Efficient Algorithms for t-distributed Stochastic Neighborhood Embedding
• KAN: Kolmogorov-Arnold Networks
• Gemma 2: Improving Open Language Models at a Practical Size
• Qwen2.5 Technical Report
• MOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis in Online Opinion Videos

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering