Causal Discovery with Language Models as Imperfect Experts
Abstract
Understanding the causal relationships that underlie a system is a fundamental prerequisite to accurate decision-making. In this work, we explore how expert knowledge can be used to improve the data-driven identification of causal graphs, beyond Markov equivalence classes. In doing so, we consider a setting where we can query an expert about the orientation of causal relationships between variables, but where the expert may provide erroneous information. We propose strategies for amending such expert knowledge based on consistency properties, e.g., acyclicity and conditional independencies in the equivalence class. We then report a case study, on real data, where a large language model is used as an imperfect expert.
Cite
@article{arxiv.2307.02390,
title = {Causal Discovery with Language Models as Imperfect Experts},
author = {Stephanie Long and Alexandre Piché and Valentina Zantedeschi and Tibor Schuster and Alexandre Drouin},
journal= {arXiv preprint arXiv:2307.02390},
year = {2023}
}
Comments
Peer reviewed and accepted for presentation at the Structured Probabilistic Inference & Generative Modeling (SPIGM) workshop at ICML 2023, Hawaii, USA