Can large language models build causal graphs?
This addresses the challenge for researchers and clinicians in building causal graphs, but it appears incremental as it focuses on evaluating existing LLMs rather than introducing a new method.
The paper tackled the problem of labor-intensive causal graph construction by evaluating whether large language models (LLMs) can complement this process through automatic edge scoring, but the abstract does not specify concrete results or numbers.
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 words, context, and prompts that the user employs. In this work, we evaluate if LLMs can be a useful tool in complementing causal graph development.