Document Type

Article

Publication Date

2025

DOI

10.1007/s00521-025-11157-x

Publication Title

Neural Computing and Applications

Volume

Article in Press

Pages

18 pp.

Abstract

Fuzzy Cognitive Maps (FCMs) are interpretable simulation models that represent causal relationships between concepts as a weighted digraph with labeled nodes. They serve to examine a system’s structure (e.g., what concepts are critical to spreading an intervention’s effects?) and long-term behavior (e.g., if we increase fruit availability, how will its consumption change?). When modelers build FCMs by leveraging participants’ knowledge, the resulting participant-built FCMs can be analyzed and interpreted since participants report perceived causality. However, engaging enough knowledgeable participants to construct an FCM can be challenging. Alternatively, machine learning algorithms derive FCMs from data by selecting relationships to maximize a metric such as accuracy, which can produce overly dense FCMs where relationships may not represent valid causal mechanisms—this hinders the critically important interpretability of FCMs. In this paper, we address the need for expert knowledge and the validity of causal mechanisms in FCMs. Specifically, we propose using Large Language Models (LLMs) to guide algorithms in building FCMs where valid pairs of concepts are connected in the right causal direction and with the correct causal type (increase/decrease). Our approach combines LLMs with CMA-ES, a ubiquitous, state-of-the-art evolutionary algorithm. Using three real-world case studies and several LLMs, we show our method successfully (i) learns sparse FCMs that fit the data well and (ii) represents valid causal relationships. Moreover, the learned FCMs are sparser than the corresponding participant-built ones, demonstrating our method may help simplify existing FCMs and selectively includes causal relationships, which is essential to build trustworthy and interpretable FCMs.

Rights

© 2025 The Authors.

This article is licensed under a Creative Commons Attribution 4.0 International (CC BY 4.0) License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original authors and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.

Data Availability

Article states: "We include input files for the diabetes and municipal governance case studies and our results files at the following URL: https://zenodo.org/records/11194343. The data for the nutrition case study can be requested from the authors of the original study."

Original Publication Citation

Schuerkamp, R., & Giabbanelli, P. J. (2025). Guiding evolutionary algorithms with large language models to learn fuzzy cognitive maps. Neural Computing and Applications. Advance online publication. https://doi.org/10.1007/s00521-025-11157-x

ORCID

0000-0001-6816-355X (Giabbanelli)

Download

Share

COinS