mlsanityData to 7 Oct 2026

Exploring Cognitive and Aesthetic Causality for Multimodal Aspect-Based Sentiment Analysis

arXiv 2504.15848 ↗First posted 22 Apr 2025cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Multimodal aspect-based sentiment classification (MASC) is an emerging task due to an increase in user-generated multimodal content on social platforms, aimed at predicting sentiment polarity toward specific aspect targets (i.e., entities or attributes explicitly mentioned in text-image pairs). Despite extensive efforts and significant achievements in existing MASC, substantial gaps remain in understanding fine-grained visual content and the cognitive rationales derived from semantic content and impressions (cognitive interpretations of emotions evoked by image content). In this study, we present Chimera: a cognitive and aesthetic sentiment causality understanding framework to derive fine-grained holistic features of aspects and infer the fundamental drivers of sentiment expression from both semantic perspectives and affective-cognitive resonance (the synergistic effect between emotional responses and cognitive interpretations). Specifically, this framework first incorporates visual patch features for patch-word alignment. Meanwhile, it extracts coarse-grained visual features (e.g., overall image representation) and fine-grained visual regions (e.g., aspect-related regions) and translates them into corresponding textual descriptions (e.g., facial, aesthetic). Finally, we leverage the sentimental causes and impressions generated by a large language model (LLM) to enhance the model's awareness of sentimental cues evoked by semantic content and affective-cognitive resonance. Experimental results on standard MASC datasets demonstrate the effectiveness of the proposed model, which also exhibits greater flexibility to MASC compared to LLMs such as GPT-4o. We have publicly released the complete implementation and dataset at https://github.com/Xillv/Chimera

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 38 of its 105 references that are in the map. First posted on arXiv 22 Apr 2025.

Builds on

38 of 105 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2023GPT-4 Technical Reportcited by 18,132
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  6. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  7. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  8. 2023PaLM 2 Technical Reportcited by 1,154
  9. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,135
  10. 2024Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunitiescited by 247
  11. 2021AdaViT: Adaptive Vision Transformers for Efficient Image Recognitioncited by 228
  12. 2021Reframing Human-AI Collaboration for Generating Free-Text Explanationscited by 125
26 more
  1. 2023SCOTT: Self-Consistent Chain-of-Thought Distillationcited by 103
  2. 2023Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Modelscited by 87
  3. 2021Sample and Computation Redistribution for Efficient Face Detectioncited by 86
  4. 2016Aspect Level Sentiment Classification with Deep Memory Networkcited by 82
  5. 2023GPTEval: A Survey on Assessments of ChatGPT and GPT-4cited by 73
  6. 2022TweetNLP: Cutting-Edge Natural Language Processing for Social Mediacited by 71
  7. 2023VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretrainingcited by 63
  8. 2023Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Taskscited by 62
  9. 2022A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challengescited by 61
  10. 2022PINTO: Faithful Language Reasoning Using Prompt-Generated Rationalescited by 56
  11. 2024Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learningcited by 47
  12. 2021Exploiting BERT For Multimodal Target Sentiment Classification Through Input Space Translationcited by 41
  13. 2019Integrating Text and Image: Determining Multimodal Document Intent in Instagram Postscited by 37
  14. 2023LogiCoT: Logical Chain-of-Thought Instruction-Tuningcited by 31
  15. 2021Self-slimmed Vision Transformercited by 27
  16. 2022Towards Multi-Modal Sarcasm Detection via Hierarchical Congruity Modeling with Knowledge Enhancementcited by 26
  17. 2024Facial Affective Behavior Analysis with Instruction Tuningcited by 26
  18. 2022Vision-Language Pre-Training for Multimodal Aspect-Based Sentiment Analysiscited by 21
  19. 2019Aesthetic Attributes Assessment of Imagescited by 18
  20. 2023Interpretable Multimodal Misinformation Detection with Logic Reasoningcited by 16
  21. 2025Uni-Retrieval: A Multi-Style Retrieval Framework for STEM's Educationcited by 13
  22. 2023Robust Domain Misinformation Detection via Multi-modal Feature Alignmentcited by 10
  23. 2023AoM: Detecting Aspect-oriented Information for Multimodal Aspect-Based Sentiment Analysiscited by 9
  24. 2023M2DF: Multi-grained Multi-curriculum Denoising Framework for Multimodal Aspect-based Sentiment Analysiscited by 6
  25. 2022Target-oriented Sentiment Classification with Sequential Cross-modal Semantic Graphcited by 2
  26. 2023RethinkingTMSC: An Empirical Study for Target-Oriented Multimodal Sentiment Classificationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 1.

6 papers.

  1. 2025Towards Robust Evaluation of STEM Education: Leveraging MLLMs in Project-Based Learningcited by 7
  2. 2025Affective-ROPTester: Capability and Bias Analysis of LLMs in Predicting Retinopathy of Prematuritycited by 3
  3. 2025From Query to Explanation: Uni-RAG for Multi-Modal Retrieval-Augmented Learning in STEMcited by 2
  4. 2025Multimodal LLMs See Sentimentcited by 2
  5. 2025Semantic-preserved Augmentation with Confidence-weighted Fine-tuning for Aspect Category Sentiment Analysiscited by 0
  6. 2026Beyond Heuristic Prompting: A Concept-Guided Bayesian Framework for Zero-Shot Image Recognitioncited by 0