Beauty is in the AI of the beholder: MLLMs systematically overrate facial attractiveness
On the map: Multimodal LLMs / vision-language models → Social bias and fairness in VLMs
Abstract (arXiv)
Beauty assessments from Multimodal Large Language Models (MLLMs) are increasingly popular amongst users, companies, and aestheticians. This raises the question of whether these AI models can accurately reflect human judgments of attractiveness. In a pre- registered exploratory study, we compared the attractiveness ratings of 2,513 human participants to four widely used commercial AI models: Claude, Gemini, GPT, and Grok. Results showed that MLLMs systematically rate faces more favourably and within a narrower range than humans and, at the time of study, do not reproduce human ratings in absolute terms. However, MLLMs exhibit strong correlations with human attractiveness judgments, accurately tracking the rank-ordering of faces. MLLMs may judge faces by different cues than humans; only face age was a predictor of facial attractiveness in both humans and MLLMs, with inconsistent patterns across models for ethnicity and gender. AI models strongly agree with one another, except for Grok, which also showed the lowest agreement with humans. Our findings suggest that while they may be able to approximate rank-orderings of human attractiveness, current off-the-shelf commercial MLLMs systematically overrate the beauty of human faces.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Social bias and fairness in VLMs, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 16 of its 72 references that are in the map. First posted on arXiv 2 Sep 2026.
Builds on
16 of 72 references.
Closest ancestors · 3
Same direction, newest first
- 2026Out of the box age estimation through facial imagery: A Comprehensive Benchmark of Vision-Language Models vs. out-of-the-box Traditional Architectures8 Feb
- 2025FaceXBench: Evaluating Multimodal LLMs on Face Understanding17 Jan
- 2024Social Perception of Faces in a Vision-Language Model26 Aug
Other references · 13
- 2017Attention Is All You Needcited by 60,361
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
- 2023Towards Understanding Sycophancy in Language Modelscited by 1,040
- 2024Refusal in Language Models Is Mediated by a Single Directioncited by 1,032
- 2021Multimodal datasets: misogyny, pornography, and malignant stereotypescited by 327
- 2024Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Modelscited by 167
- 2024Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversationscited by 129
- 2023Brain encoding models based on multimodal transformers can transfer across language and visioncited by 32
- 2024Can ChatGPT evaluate research quality?cited by 17
- 2025Beauty and the Bias: Exploring the Impact of Attractiveness on Multimodal Large Language Modelscited by 7
- 2024FaceGPT: Self-supervised Learning to Chat about 3D Human Facescited by 4
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026StylisticBias: A Few Human Visual Cues Drive Most Social Biases in MLLMs
- 2026Aesthetics as Structural Harm: Algorithmic Lookism Across Text-to-Image Generation and Classification
- 2026Interoceptive Divergence in Aesthetic Evaluation and Implications for Human-AI Alignment
- 2024Dataset Scale and Societal Consistency Mediate Facial Impression Bias in Vision-Language AI
- 2025AesBiasBench: Evaluating Bias and Alignment in Multimodal Language Models for Personalized Image Aesthetic Assessment
- 2022Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias
- 2024AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perception
- 2024"My Kind of Woman": Analysing Gender Stereotypes in AI through The Averageness Theory and EU Law