Update README.md

README.md

@@ -17,6 +17,8 @@ Eric Hartford and Quixi.ai present ReAligned Classifier, a lightweight bias dete
 
 ReAligned Classifier outputs calibrated probabilities suitable for use as continuous reward signals.
 
+Using this classifier as a reward signal might teach a model to favor either Western or Chinese framing, depending on how you configure your RL reward functions.
+
 ## Model Architecture
 
 - **Base Model:** meta-llama/Llama-3.2-1B