Nick Huntington-Klein @nickchk.com · Dec 17 So let's test how well it does at that. We use the Coronary Drug Project, an experimental study that faced poor treatment adherence in its placebo arm, introducing confounding. Several studies have built necessary adjustment sets using expert opinion. *The LLM can see those studies.*
2 likes 1 replies
?
Replies
So if we feed back the list of potential confounders those studies discussed and ask the LLMs whether each is a confounder, it should be able to tell us, right? Well, not really. Performance is decidedly mediocre.