Large language models for causal hypothesis generation in science
Machine Learning: Science and Technology · 31.03.2025 · 6 (1) · 013001
DOI: 10.1088/2632-2153/ada47f ↗Kurz gefasst
Fachartikel in der Zeitschrift Machine Learning: Science and Technology, online erschienen am 31.01.2025. Verfasst von Kai-Hendrik Cohrs und 4 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 186 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Research Council, Fundación BBVA, Conselleria de Innovación, Universidades, Ciencia y Sociedad Digital, Generalitat Valenciana.
Abstract (Originalsprache)
Towards the goal of understanding the causal structure underlying complex systems—such as the Earth, the climate, or the brain—integrating Large language models (LLMs) with data-driven and domain-expertise-driven approaches has the potential to become a game-changer, especially in data and expertise-limited scenarios. Debates persist around LLMs’ causal reasoning capacities. However, rather than engaging in philosophical debates, we propose integrating LLMs into a scientific framework for causal hypothesis generation alongside expert knowledge and data. Our goals include formalizing LLMs as probabilistic imperfect experts, developing adaptive methods for causal hypothesis generation, and establishing universal benchmarks for comprehensive comparisons. Specifically, we introduce a spectrum of integration methods for experts, LLMs, and data-driven approaches. We review existing approaches for causal hypothesis generation and classify them within this spectrum. As an example, our hybrid (LLM + data) causal discovery algorithm illustrates ways for deeper integration. Characterizing imperfect experts along dimensions such as (1) reliability, (2) consistency, (3) uncertainty, and (4) content vs. reasoning are emphasized for developing adaptable methods. Lastly, we stress the importance of model-agnostic benchmarks.
Förderung
- European Research Council
- Fundación BBVA
- Conselleria de Innovación, Universidades, Ciencia y Sociedad Digital, Generalitat Valenciana
- Microsoft Research
Zitieren
APA
Cohrs, K., Diaz, E., Sitokonstantinou, V., Varando, G., & Camps-Valls, G. (2025). Large language models for causal hypothesis generation in science. Machine Learning: Science and Technology, 6(1), 013001. https://doi.org/10.1088/2632-2153/ada47f
Vancouver
Cohrs K, Diaz E, Sitokonstantinou V, Varando G, Camps-Valls G. Large language models for causal hypothesis generation in science. Machine Learning: Science and Technology. 2025;6(1):013001. doi:10.1088/2632-2153/ada47f
BibTeX
@article{Cohrs2025,
author = {Cohrs, Kai-Hendrik and Diaz, Emiliano and Sitokonstantinou, Vasileios and Varando, Gherardo and Camps-Valls, Gustau},
title = {Large language models for causal hypothesis generation in science},
journal = {Machine Learning: Science and Technology},
year = {2025},
volume = {6},
number = {1},
pages = {013001},
doi = {10.1088/2632-2153/ada47f}
}
EUVIMED