Causal Graph Discovery with Retrieval-Augmented Generation based Large Language Models

Understand

Causal graph recovery is traditionally done using statistical estimation-based methods or based on individual's knowledge about variables of interests.

• They often suffer from data collection biases and limitations of individuals' knowledge.
• The advance of large language models (LLMs) provides opportunities to address these problems.
• We propose a novel method that leverages LLMs to deduce causal relationships in general causal graph recovery tasks.