# Multimodal LLMs Can Reason about Aesthetics in Zero-Shot

arXiv: https://arxiv.org/abs/2501.09012 · HTML: https://mlsanity.com/paper/2501.09012/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 22 of its 98 references that are in the map.
- First posted on arXiv 15 Jan 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [Image editing and quality assessment](https://mlsanity.com/mllm/image-editing-and-quality-assessment/)

## Builds on (most cited first, 22 of 22)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [Training Large Language Models to Reason in a Continuous Latent Space](https://mlsanity.com/paper/2412.06769/) (2024)
- [Directly Fine-Tuning Diffusion Models on Differentiable Rewards](https://mlsanity.com/paper/2309.17400/) (2023)
- [Hallucination of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2404.18930/) (2024)
- [DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models](https://mlsanity.com/paper/2210.14896/) (2022)
- [To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning](https://mlsanity.com/paper/2409.12183/) (2024)
- [Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation](https://mlsanity.com/paper/2402.17245/) (2024)
- [InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation](https://mlsanity.com/paper/2404.02733/) (2024)
- [GPT-4V(ision) as a Generalist Evaluator for Vision-Language Tasks](https://mlsanity.com/paper/2311.01361/) (2023)
- [Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse](https://mlsanity.com/paper/2410.21333/) (2024)
- [CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Norms](https://mlsanity.com/paper/1706.07068/) (2017)
- [Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare](https://mlsanity.com/paper/2405.19298/) (2024)
- [The ArtBench Dataset: Benchmarking Generative Models with Artworks](https://mlsanity.com/paper/2206.11404/) (2022)
- [StyleShot: A Snapshot on Any Style](https://mlsanity.com/paper/2407.01414/) (2024)
- [ArtGPT-4: Towards Artistic-understanding Large Vision-Language Models with Enhanced Adapter](https://mlsanity.com/paper/2305.07490/) (2023)
- [Formal Analysis of Art: Proxy Learning of Visual Concepts from Style Through Language Models](https://mlsanity.com/paper/2201.01819/) (2022)
- [DiffArtist: Towards Structure and Appearance Controllable Image Stylization](https://mlsanity.com/paper/2407.15842/) (2024)
- [Artificial Intelligence and Aesthetic Judgment](https://mlsanity.com/paper/2309.12338/) (2023)

## Built on by (most cited first, 14 of 14)

- [Fine-Grained Zero-Shot Object Detection](https://mlsanity.com/paper/2507.10358/) (2025)
- [LookBench: A Live and Holistic Open Benchmark for Fashion Image Retrieval](https://mlsanity.com/paper/2601.14706/) (2026)
- [Cognitive Mismatch in Multimodal Large Language Models for Discrete Symbol Understanding](https://mlsanity.com/paper/2603.18472/) (2026)
- [Can Vision Language Models Assess Graphic Design Aesthetics? A Benchmark, Evaluation, and Dataset Perspective](https://mlsanity.com/paper/2603.01083/) (2026)
- [Venus: Benchmarking and Empowering Multimodal Large Language Models for Aesthetic Guidance and Cropping](https://mlsanity.com/paper/2602.23980/) (2026)
- [CROP: Expert-Aligned Image Cropping via Compositional Reasoning and Optimizing Preference](https://mlsanity.com/paper/2605.12545/) (2026)
- [From Concepts to Judgments: Interpretable Image Aesthetic Assessment](https://mlsanity.com/paper/2603.18108/) (2026)
- [PhotoAgent: A Robotic Photographer with Spatial and Aesthetic Understanding](https://mlsanity.com/paper/2603.22796/) (2026)
- [On Semiotic-Grounded Interpretive Evaluation of Generative Art](https://mlsanity.com/paper/2604.08641/) (2026)
- [Beyond Fidelity: Semantic Similarity Assessment in Low-Level Image Processing](https://mlsanity.com/paper/2604.25408/) (2026)
- [Before the Shutter: Aesthetic and Actionable Portrait Photography Planning in 3D Scenes](https://mlsanity.com/paper/2605.30318/) (2026)
- [Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation](https://mlsanity.com/paper/2607.11886/) (2026)
- [Robustness of AI-Art Detectors under Generator Shift](https://mlsanity.com/paper/2608.11643/) (2026)
- [SE-MoLoRA: Shared-Expert LoRA Adapters for Domain-Specific Photographic Assessment](https://mlsanity.com/paper/2608.17514/) (2026)

## Abstract (arXiv)

The rapid technical progress of generative art (GenArt) has democratized the creation of visually appealing imagery. However, achieving genuine artistic impact - the kind that resonates with viewers on a deeper, more meaningful level - remains formidable as it requires a sophisticated aesthetic sensibility. This sensibility involves a multifaceted cognitive process extending beyond mere visual appeal, which is often overlooked by current computational methods. This paper pioneers an approach to capture this complex process by investigating how the reasoning capabilities of Multimodal LLMs (MLLMs) can be effectively elicited to perform aesthetic judgment. Our analysis reveals a critical challenge: MLLMs exhibit a tendency towards hallucinations during aesthetic reasoning, characterized by subjective opinions and unsubstantiated artistic interpretations. We further demonstrate that these hallucinations can be suppressed by employing an evidence-based and objective reasoning process, as substantiated by our proposed baseline, ArtCoT. MLLMs prompted by this principle produce multifaceted, in-depth aesthetic reasoning that aligns significantly better with human judgment. These findings have direct applications in areas such as AI art tutoring and as reward models for image generation. Ultimately, we hope this work paves the way for AI systems that can truly understand, appreciate, and contribute to art that aligns with human aesthetic values. Project homepage: https://github.com/songrise/MLLM4Art.