Artwork Interpretation with Vision Language Models: A Case Study on Emotions and Emotion Symbols
On the map: Multimodal LLMs / vision-language models → Multimodal emotion understanding
Abstract (arXiv)
Emotions are a fundamental aspect of artistic expression. Due to their abstract nature, there is a broad spectrum of emotion realization in artworks. These are subject to historical change and their analysis requires expertise in art history. In this article, we investigate which aspects of emotional expression can be detected by current (2025) vision language models (VLMs). We present a case study of three VLMs (Llava-Llama and two Qwen models) in which we ask these models four sets of questions of increasing complexity about artworks (general content, emotional content, expression of emotions, and emotion symbols) and carry out a qualitative expert evaluation. We find that the VLMs recognize the content of the images surprisingly well and often also which emotions they depict and how they are expressed. The models perform best for concrete images but fail for highly abstract or highly symbolic images. Reliable recognition of symbols remains fundamentally difficult. Furthermore, the models continue to exhibit the well-known LLM weakness of providing inconsistent answers to related questions.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Multimodal emotion understanding, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 15 of its 60 references that are in the map. First posted on arXiv 28 Nov 2025.
Builds on
15 of 60 references.
References · 15
- 2017Attention Is All You Needcited by 59,932
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2015VQA: Visual Question Answeringcited by 2,489
- 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,219
- 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,234
- 2023Vision-Language Models for Vision Tasks: A Surveycited by 834
- 2024Chain-of-Thought Reasoning Without Promptingcited by 208
- 2024Cognitive Bias in Decision-Making with LLMscited by 104
- 2025DeepSeek-R1 Thoughtology: Let's think about LLM Reasoningcited by 91
- 2023Opening up ChatGPT: Tracking openness, transparency, and accountability in instruction-tuned text generatorscited by 56
- 2024Understanding the Capabilities and Limitations of Large Language Models for Cultural Commonsensecited by 50
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2024Training A Small Emotional Vision Language Model for Visual Art Comprehension
- 2024Have Large Vision-Language Models Mastered Art History?
- 2025CognArtive: Large Language Models for Automating Art Analysis and Decoding Aesthetic Elements
- 2026Does AI See like Art Historians? Interpreting How Vision Language Models Recognize Artistic Style
- 2026Why Do Vision Language Models Struggle To Recognize Human Emotions?
- 2026ArtECulture: Benchmarking Culture-Conditioned Visual Emotion Understanding in Multimodal Large Language Models
- 2025Evaluating Vision-Language Models for Emotion Recognition
- 2026MMArt: A Multi-Perspective Multimodal Dataset for Visual Art Understanding