English

Causality Elicitation from Large Language Models

Machine Learning 2026-03-05 v1 Artificial Intelligence Computation and Language Econometrics

Abstract

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.

Keywords

Cite

@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}
}
R2 v1 2026-07-01T11:03:25.636Z