Can large language models build causal graphs?

arXiv:2303.05279v2 Announce Type: replace
Abstract: Building causal graphs can be a laborious process. To ensure all relevant causal pathways have been captured, researchers often have to discuss with clinicians and experts while also reviewing extensive relevant medical literature. By encoding common and medical knowledge, large language models (LLMs) represent an opportunity to ease this process by automatically scoring edges (i.e., connections between two variables) in potential graphs. LLMs however have been shown to be brittle to the choice of probing …

abstract arxiv build building clinicians cs.ai cs.cl discuss encoding experts graphs knowledge language language models large language large language models literature llms medical process researchers type