High variability in LLMs' analogical reasoning

Andrea Gregor de Varda^{1

2}, Chiara Saponaro³, Marco Marelli³

Affiliations

¹ Department of Psychology, University of Milano - Bicocca, Milan, Italy. devar_ag@mit.edu.
² Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA, USA. devar_ag@mit.edu.
³ Department of Psychology, University of Milano - Bicocca, Milan, Italy.

Andrea Gregor de Varda et al. Nat Hum Behav. 2025 Jul.

. 2025 Jul;9(7):1339-1341.

doi: 10.1038/s41562-025-02224-3. Epub 2025 Jun 4.

Andrea Gregor de Varda^{1

2}, Chiara Saponaro³, Marco Marelli³

¹ Department of Psychology, University of Milano - Bicocca, Milan, Italy. devar_ag@mit.edu.
² Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA, USA. devar_ag@mit.edu.
³ Department of Psychology, University of Milano - Bicocca, Milan, Italy.

No abstract available

Conflict of interest statement

Competing interests: The authors declare no competing interests.

1. Webb, T., Holyoak, K. J. & Lu, H. Emergent analogical reasoning in large language models. Nat. Hum. Behav. 7, 1526–1541 (2023). - PubMed
1. Hu, J. & Levy, R. P. Prompting is not a substitute for probability measurements in large language models. In Proc. 2023 Conference on Empirical Methods in Natural Language Processing (eds Bouamor, H. et al.) 5040–5060 (Association for Computational Linguistics, 2023).
1. Binz, M. et al. How should the advancement of large language models affect the practice of science? Proc. Natl Acad. Sci. 122, e2401227121 (2025). - PubMed - PMC
1. Brodeur, A., Dreber, A., Hoces de la Guardia, F. & Miguel, E. Reproduction and replication at scale. Nat. Hum. Behav. 8, 2–3 (2024). - PubMed
1. Gunasekar, S. et al. Textbooks are all you need. Preprint at https://doi.org/10.48550/arXiv.2306.11644 (2023).