Gromov–Wasserstein unsupervised alignment reveals structural correspondences between the color similarity structures of humans and large language models | Scientific Reports

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript. Advertisement Scientific Reports volume 14, Article number: 15917 (2024) Cite this article 3777 Accesses 17 Citations 17 Altmetric Metrics details 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

Download PDF Subjects Computational neuroscience Human behaviour Abstract 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- lev

related reading

• Verbalizable Representations Form a Global Workspace in Language Modelstransformer-circuits.pub
• transformer_attention.pdfarxiv.org
• High-level visual representations in the human brain are aligned with large language models | Nature Machine Intelligencenature.com
• [2305.18290] Direct Preference Optimization: Your Language Model is Secretly a Reward Modelarxiv.org
• [2210.13382] Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskarxiv.org
• [2005.14165] Language Models are Few-Shot Learnersarxiv.org
• Language models can explain neurons in language modelsopenaipublic.blob.core.windows.net
• Large language models surpass human experts in predicting neuroscience resultsnature.com
• Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskarxiv.org
• Large Language Model: world models or surface statistics?thegradient.pub
• [2602.15029] Symmetry in language statistics shapes the geometry of model representationsarxiv.org
• Symmetry in language statistics shapes the geometry of model representationsarxiv.org