Causal Discovery with Foundation Models: Evidence, Assumptions, and Evaluation

Authors

  • Paul Hughes Author

Keywords:

causal discovery, foundation models, identifiability, evaluation, scientific AI

Abstract

This methods review examines causal discovery with foundation models. The organizing question is when foundation-model representations can support causal structure learning rather than reproduce observational association. Ten related scholarly sources are synthesized through a decision-centered framework spanning problem definition, mechanism, measurement, evaluation, implementation, and governance. The review does not invent experiments, pooled estimates, or unreported quantitative results. It instead evaluates the strength and transferability of the available evidence, with particular attention to using fluent causal explanations as substitutes for identifiability assumptions. The resulting framework links technical or empirical performance to explicit use conditions and identifies tests that should precede wider adoption in scientific discovery and decision support.

References

  1. Anderson, M., & Müller, A. (2025). Causal Discovery in Multi-Echelon Supply Networks: Leveraging Foundation Models for Demand Propagation Analysis. Frontiers in Applied Physics and Mathematics, 2(1), 114-129. https://doi.org/10.71465/fapm416
  2. Giarmatzi, C., & Costa, F. (2018). A quantum causal discovery algorithm. npj Quantum Information, 4(1). https://doi.org/10.1038/s41534-018-0062-6
  3. Glaser, J., & Laudel, G. (2019). The Discovery of Causal Mechanisms: Extractive Qualitative Content Analysis as a Tool for Process. Social Science Open Access Repository (GESIS – Leibniz Institute for the Social Sciences). https://doi.org/10.17169/fqs-20.3.3386
  4. Glymour, C., Zhang, K., & Spirtes, P. (2019). Review of Causal Discovery Methods Based on Graphical Models. Frontiers in Genetics, 10, 524. https://doi.org/10.3389/fgene.2019.00524
  5. Kıcıman, E., Ness, R., Sharma, A., & Tan, C. (2023). Causal Reasoning and Large Language Models: Opening a New Frontier for Causality. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2305.00050
  6. Ma, P., Ji, Z., Pang, Q., & Wang, S. (2022). NoLeaks: Differentially Private Causal Discovery Under Functional Causal Model. IEEE Transactions on Information Forensics and Security, 17, 2324-2338. https://doi.org/10.1109/tifs.2022.3184263
  7. Saxe, G. N., Statnikov, A., Fenyo, D., Ren, J., Li, Z., Prasad, M., Wall, D., Bergman, N., Briggs, E. C., & Aliferis, C. (2016). A Complex Systems Approach to Causal Discovery in Psychiatry. PLoS ONE, 11(3), e0151174. https://doi.org/10.1371/journal.pone.0151174
  8. Stips, A., Macias, D., Coughlan, C., Garcia-Gorriz, E., & Liang, X. S. (2016). On the causal structure between CO2 and global temperature. Scientific Reports, 6(1), 21691. https://doi.org/10.1038/srep21691
  9. Wang, L., Huang, S., Wang, S., Liao, J., Li, T., & Liu, L. (2024). A survey of causal discovery based on functional causal model. Engineering Applications of Artificial Intelligence, 133, 108258. https://doi.org/10.1016/j.engappai.2024.108258
  10. Zheng, H., Petrella, J. R., Doraiswamy, P. M., Lin, G., Hao, W., & Initiative, F. T. A. S. D. N. (2022). Data-driven causal model discovery and personalized prediction in Alzheimer's disease. npj Digital Medicine, 5(1), 137. https://doi.org/10.1038/s41746-022-00632-7

Downloads

Published

2026-08-08

Issue

Vol. 1 (2026): Archive

Section

Methods Review

License

Copyright (c) 2026 Journal of Algorithmic Discovery and Applied AI

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.