How Humans and LLMs Organize Conceptual Knowledge: Exploring Subordinate Categories in Italian

Andrea Pedrotti, Giulia Rambelli, Caterina Villani, Marianna Bolognesi
5/27/2025
cs.CLcs.AI

No official code found. Best implementation: andreapdr/conceptCategoriesLLMs (2 stars, last commit 2025-06-04).

Abstract

People can categorize the same entity at multiple taxonomic levels, such as basic (bear), superordinate (animal), and subordinate (grizzly bear). While prior research has focused on basic-level categories, this study is the first attempt to examine the organization of categories by analyzing exemplars produced at the subordinate level. We present a new Italian psycholinguistic dataset of human-generated exemplars for 187 concrete words. We then use these data to evaluate whether textual and vision LLMs produce meaningful exemplars that align with human category organization across three key tasks: exemplar generation, category induction, and typicality judgment. Our findings show a low alignment between humans and LLMs, consistent with previous studies. However, their performance varies notably across different semantic domains. Ultimately, this study highlights both the promises and the constraints of using AI-generated exemplars to support psychological and linguistic research.

View on arXivView PDF

Code Implementations(1)

andreapdr/conceptCategoriesLLMsCommunity68%

How Humans and LLMs Organize Conceptual Knowledge: Exploring Subordinate Categories in Italian (ACL 2025)

20Python, Jupyter NotebookOct 22, 20241 years ago

Similar Papers

Conceptual structure coheres in human cognition but not in large language models

82% match2023

Human-like object concept representations emerge naturally in multimodal large language models

82% match2024

Revealing emergent human-like conceptual representations from language prediction

82% match1 repo132025

Humanlike Cognitive Patterns as Emergent Phenomena in Large Language Models

80% match2024

Cobweb: An Incremental and Hierarchical Model of Human-Like Category Learning

80% match1 repo2024

Improving Alignment Between Human and Machine Codes: An Empirical Assessment of Prompt Engineering for Construct Identification in Psychology

80% match2025

Cite this paper

@article{pedrotti2025humans,
  title  = {How Humans and LLMs Organize Conceptual Knowledge: Exploring Subordinate Categories in Italian},
  author = {Andrea Pedrotti and Giulia Rambelli and Caterina Villani and Marianna Bolognesi},
  year   = {2025},
  eprint = {2505.21301},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2505.21301v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2505.21301.svg)](https://codeofpaper.com/paper/2505.21301)

Discussion