# Gromov-Wasserstein unsupervised alignment reveals structural correspondences between the color similarity structures of humans and large language models

arXiv: https://arxiv.org/abs/2308.04381 · HTML: https://mlsanity.com/paper/2308.04381/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Aug 2023.

## Built on by (most cited first, 16 of 16)

- [Human-like object concept representations emerge naturally in multimodal large language models](https://mlsanity.com/paper/2407.01067/) (2024)
- [Levels of Analysis for Large Language Models](https://mlsanity.com/paper/2503.13401/) (2025)
- [Source-Free Domain Adaptation for YOLO Object Detection](https://mlsanity.com/paper/2409.16538/) (2024)
- [COLIBRI Fuzzy Model: Color Linguistic-Based Representation and Interpretation](https://mlsanity.com/paper/2507.11488/) (2025)
- [Constructive Approach to Bidirectional Influence between Qualia Structure and Language Emergence](https://mlsanity.com/paper/2409.09413/) (2024)
- [The Zero Body Problem: Probing LLM Use of Sensory Language](https://mlsanity.com/paper/2504.06393/) (2025)
- [The Limits of Learning from Pictures and Text: Vision-Language Models and Embodied Scene Understanding](https://mlsanity.com/paper/2603.26589/) (2026)
- [Advancements and limitations of LLMs in replicating human color-word associations](https://mlsanity.com/paper/2411.02116/) (2024)
- [Correspondence of high-dimensional emotion structures elicited by video clips between humans and Multimodal LLMs](https://mlsanity.com/paper/2505.12746/) (2025)
- [Neural Correlates of Language Models Are Specific to Human Language](https://mlsanity.com/paper/2510.03156/) (2025)
- [Dialectical Behavior Therapy Approach to LLM Prompting](https://mlsanity.com/paper/2410.07768/) (2024)
- [Investigating Fine- and Coarse-grained Structural Correspondences Between Deep Neural Networks and Human Object Image Similarity Judgments Using Unsupervised Alignment](https://mlsanity.com/paper/2505.16419/) (2025)
- [Engineering Sentience](https://mlsanity.com/paper/2506.20504/) (2025)
- [Measuring How LLMs Internalize Human Psychological Concepts: A preliminary analysis](https://mlsanity.com/paper/2506.23055/) (2025)
- [ColorGPT: Leveraging Large Language Models for Multimodal Color Recommendation](https://mlsanity.com/paper/2508.08987/) (2025)
- [Averaged Mirror Descent and Dual Gradient Methods: Convergent Algorithms for Entropic Gromov-Wasserstein Problems](https://mlsanity.com/paper/2609.31848/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs), such as the General Pre-trained Transformer (GPT), have shown remarkable performance in various cognitive tasks. However, it remains unclear whether these models have the ability to accurately infer human perceptual representations. Previous research has addressed this question by quantifying correlations between similarity response patterns of humans and LLMs. Correlation provides a measure of similarity, but it relies pre-defined item labels and does not distinguish category- and item- level similarity, falling short of characterizing detailed structural correspondence between humans and LLMs. To assess their structural equivalence in more detail, we propose the use of an unsupervised alignment method based on Gromov-Wasserstein optimal transport (GWOT). GWOT allows for the comparison of similarity structures without relying on pre-defined label correspondences and can reveal fine-grained structural similarities and differences that may not be detected by simple correlation analysis. Using a large dataset of similarity judgments of 93 colors, we compared the color similarity structures of humans (color-neurotypical and color-atypical participants) and two GPT models (GPT-3.5 and GPT-4). Our results show that the similarity structure of color-neurotypical participants can be remarkably well aligned with that of GPT-4 and, to a lesser extent, to that of GPT-3.5. These results contribute to the methodological advancements of comparing LLMs with human perception, and highlight the potential of unsupervised alignment methods to reveal detailed structural correspondences. This work has been published in Scientific Reports, DOI: https://doi.org/10.1038/s41598-024-65604-1.