Update README.md

README.md

@@ -1,6 +1,10 @@
-A fine-tune of THUDM/GLM-4-32B-0414 using a new experimental technique for automatic unslopping.
+A fine-tune of THUDM/GLM-4-32B-0414 using the antislop method described in this paper: https://arxiv.org/abs/2510.15061
 
-The intention is to make the most common slop words & phrases much less frequent, with minimal impact to the model otherwise.
+The pipeline identifies the model's unique slop (over-represented words and phrases compared to human writing), generates a preference training set, and trains out the slop with our FTPO training algorithm.
+
+https://github.com/sam-paech/auto-antislop
+
+This process alters the model to make the most common slop words & phrases much less frequent, with minimal impact or degradation to the model.
 
 It won't remove slop entirely. The technique only targets over-represented words & phrases, not stylistic or thematic slop.