Can Socratic reflection improve #AI answers to medical questions?
General Medicine
2
Posts
1
Posters
6
Views
-
Can Socratic reflection improve #AI answers to medical questions?
Adding a critic to a #languageModel pipeline improved performance on two measures of medical question-answering.
The improvement didn't depend on the critic's model.
-
T #medicine shared this topic
-
Can Socratic reflection improve #AI answers to medical questions?
Adding a critic to a #languageModel pipeline improved performance on two measures of medical question-answering.
The improvement didn't depend on the critic's model.
This is yet another paper that finds quickly-diminishing returns of reflective thinking.
And this paper's result may be more severe: Figure 3 (above) shows accuracy on medical question-answering improved on second thought, but either plateaued or DECLINED *after* second thought.
