Update README.md

README.md

@@ -22,7 +22,7 @@ As You may notice, the dataset mostly consists of specially modified winogrande
 
 But before flagging this (or recommending this to be flagged), consider this:
 
-Subtle DPO-Contamination with modified Winogrande in such an extent that the average accuracy of all 5-non Winogrande metrics (e.g. including also MMLU and GSM8K) is 0.2% higher than the base model.
+Subtle DPO-Contamination with modified Winogrande causes the average accuracy of all 5-non Winogrande metrics (e.g. including also MMLU and GSM8K) to be 0.2% higher than the underlying model.
 
 | Model                        | ARC   | HellaSwag | MMLU | Truthful QA | GSM8K | Average |
 | -----------------------------|------ | --------- | ---- | ----------- | ------| ------- |