Large language models (LLMs) are trained on enormous amounts of data and encode knowledge in their parameters. We propose a pipeline to elicit causal relationships from LLMs. Specifically, (i) we sample many documents from LLMs on a given topic, (ii) we extract an event list from from each document, (iii) we group events that appear across documents into canonical events, (iv) we construct a binary indicator vector for each document over canonical events, and (v) we estimate candidate causal graphs using causal discovery methods. Our approach does not guarantee real-world causality. Rather, it provides a framework for presenting the set of causal hypotheses that LLMs can plausibly assume, as an inspectable set of variables and candidate graphs.
@article{arxiv.2603.04276,
title = {Causality Elicitation from Large Language Models},
author = {Takashi Kameyama and Masahiro Kato and Yasuko Hio and Yasushi Takano and Naoto Minakawa},
journal= {arXiv preprint arXiv:2603.04276},
year = {2026}
}