Causal Discovery with Language Models as Imperfect Experts
This work addresses the challenge of accurate causal discovery for decision-making systems, but it appears incremental as it builds on existing methods for handling imperfect expert input.
The paper tackles the problem of improving causal graph identification beyond Markov equivalence classes by using expert knowledge, even when the expert provides erroneous information, and demonstrates a case study with a large language model as an imperfect expert.
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.