Semantic-Aligned Structural Abstraction for Multimodal Sentiment Analysis

• URL: http://arxiv.org/abs/2607.27790v1
• Date: Thu, 30 Jul 2026 07:23:27 GMT
• Title: Semantic-Aligned Structural Abstraction for Multimodal Sentiment Analysis
• Abstract summary: Multimodal Sentiment Analysis (MSA) aims to interpret complex human emotions by integrating natural language with non-verbal modalities.<n>SentiLLM is a framework that distills continuous raw signals into compact, semantically meaningful tokens.<n>Our method achieves superior performance on four datasets, demonstrating the effectiveness of the structural abstraction paradigm in MSA.
• Score: 13.853304646673637
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal Sentiment Analysis (MSA) aims to interpret complex human emotions by integrating natural language with non-verbal modalities. Non-verbal modalities share a structural isomorphism with natural language, as both can be viewed as feature sequences evolving over time. This isomorphism enables the transformation of non-verbal modalities into text-like tokens for unified semantic reasoning. Large Language Models (LLMs), designed to understand and generate sequential data, can thus be utilized to interpret complex affective sequences. However, existing LLM-based methods primarily capture low-level superficial features, failing to model affective semantics arising from structural variations and contextual interactions. To address this limitation, we propose \textbf{SentiLLM}, a unified framework that leverages \textit{Semantic-Aligned Structural Abstraction} to distill continuous raw signals into compact, semantically meaningful tokens. Specifically, we introduce a \textit{Dual-Stream Salience-Context Calibration Mechanism}, which disentangles non-verbal feature sequences into a focus stream and an ambient stream. The focus stream captures salient sentiment shifts (e.g., facial expressions) guided by textual priors, while the ambient stream characterizes stable background states. Through calibrating these dynamic sentiment shifts against background states, SentiLLM effectively projects non-verbal modalities into a unified semantic space, making them naturally understandable for LLMs. Serving as a plug-and-play module, SentiLLM significantly improves discriminative performance with only a small number of trainable parameters. Our method achieves superior performance on four datasets, MOSI, MOSEI, CH-SIMS, and CH-SIMS v2, demonstrating the effectiveness of the structural abstraction paradigm in MSA. Our code is available at: \href{https://github.com/especiallyW/SentiLLM}.

Related papers

• Multimodal Adaptive Expert Selection with Text Routing and Ordinal Prototype Optimization for Sentiment Analysis [2.3500677765052296]
  Multimodal Sentiment Analysis (MSA) aims to decipher complex emotional states by integrating verbal content with non-verbal cues.<n>Recent disentanglement-based approaches have advanced the field, but their potential is hindered by two methodological challenges.<n>We introduce Multimodal Adaptive Expert Selection with Text Routing and Ordinal prototype optimization (MAESTRO)<n>Unlike static fusion, this module utilizes linguistic context as a routing signal to dynamically activate specific audio-visual experts.
  arXiv  Detail & Related papers  (2026-08-31T12:59:37Z)
• Dynamic Parsing and Updating Natural Language Specification using VLMs for Robust Vision-Language Tracking [61.91472604294714]
  We propose a novel language dependency parsing mechanism to distill tracking principal components.<n>We exploit the powerful cross-modal understanding capability of the pre-trained vision-language model Qwen-VL.<n>Our method achieves consistent and superior tracking performance on multiple large-scale vision-language tracking benchmarks.
  arXiv  Detail & Related papers  (2026-06-28T12:12:18Z)
• FlowSeg: Dynamic Semantic Guidance for LLM-Conditioned Segmentation [76.08991871243333]
  FlowSeg introduces semantic guidance via a bidirectional semantic flow between intermediate decoding states and condition embeddings.<n>This design yields semantically grounded mask representations and visually aligned language conditions, enabling more reliable matching.
  arXiv  Detail & Related papers  (2026-05-28T06:55:35Z)
• Seg-Agent: Test-Time Multimodal Reasoning for Training-Free Language-Guided Segmentation [52.8308168727975]
  Seg-Agent is a completely training-free framework that pioneers Explicit Multimodal Chain-of-Reasoning.<n>Our approach constructs an interactive visual reasoning loop comprising three stages: generation, selection, and refinement.<n>Various-LangSeg is a novel benchmark covering explicit semantic, generic object, and reasoning-guided segmentation tasks.
  arXiv  Detail & Related papers  (2026-05-13T03:36:44Z)
• $\mathcal{S}^2$IT: Stepwise Syntax Integration Tuning for Large Language Models in Aspect Sentiment Quad Prediction [51.165432266846096]
  syntactic structure information is underutilized in the generative paradigm of large language models (LLMs)<n>S2IT progressively integrates syntactic structure knowledge into LLMs through a multi-step tuning process.<n> Experiments demonstrate that S2IT significantly improves state-of-the-art performance across multiple datasets.
  arXiv  Detail & Related papers  (2026-04-25T13:24:29Z)
• Improving LLM Reasoning with Homophily-aware Structural and Semantic Text-Attributed Graph Compression [55.51959317490934]
  Large language models (LLMs) have demonstrated promising capabilities in Text-Attributed Graph (TAG) understanding.<n>We argue that graphs inherently contain rich structural and semantic information, and that their effective exploitation can unlock potential gains in LLMs reasoning performance.<n>We propose Homophily-aware Structural and Semantic Compression for LLMs (HS2C), a framework centered on exploiting graph homophily.
  arXiv  Detail & Related papers  (2026-01-13T03:35:18Z)
• DEFT-LLM: Disentangled Expert Feature Tuning for Micro-Expression Recognition [16.903294278064667]
  We propose DEFT-LLM, which achieves semantic alignment by multi-expert disentanglement.<n>We first introduce Uni-MER, a motion-driven instruction designed to align text with local facial motion.<n>We then design an architecture with three experts to decouple facial dynamics into independent representations.
  arXiv  Detail & Related papers  (2025-11-14T04:21:24Z)
• Temporal Sparse Autoencoders: Leveraging the Sequential Nature of Language for Interpretability [31.30541946703775]
  Translating internal representations and computations of models into concepts that humans can understand is a key goal of interpretability.<n>Recent dictionary learning methods such as Sparse Autoencoders provide a promising route to discover human-interpretable features.<n>But they exhibit a bias towards shallow, token-specific, or noisy features, such as "the phrase 'The' at the start of sentences"
  arXiv  Detail & Related papers  (2025-10-30T17:59:30Z)
• LM-SPT: LM-Aligned Semantic Distillation for Speech Tokenization [8.365515332927444]
  Recent speech tokenization approaches aim to isolate semantic information from low-level acoustics to better align with language models.<n>We propose LM-SPT, a speech tokenization method that introduces a novel semantic distillation.<n>We show that LM-SPT achieves superior reconstruction fidelity compared to baselines.
  arXiv  Detail & Related papers  (2025-06-20T04:15:14Z)
• VLLMs Provide Better Context for Emotion Understanding Through Common Sense Reasoning [66.23296689828152]
  We leverage the capabilities of Vision-and-Large-Language Models to enhance in-context emotion classification.<n>First, we prompt VLLMs to generate natural language descriptions of the subject's apparent emotion in relation to the visual context.<n>Second, the descriptions, along with the visual input, are used to train a transformer-based architecture.
  arXiv  Detail & Related papers  (2024-04-10T15:09:15Z)
• Guiding the PLMs with Semantic Anchors as Intermediate Supervision: Towards Interpretable Semantic Parsing [57.11806632758607]
  We propose to incorporate the current pretrained language models with a hierarchical decoder network. By taking the first-principle structures as the semantic anchors, we propose two novel intermediate supervision tasks. We conduct intensive experiments on several semantic parsing benchmarks and demonstrate that our approach can consistently outperform the baselines.
  arXiv  Detail & Related papers  (2022-10-04T07:27:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.