Update README.md

README.md

@@ -50,9 +50,14 @@ The Internal State of an LLM Knows When It's Lying: https://arxiv.org/pdf/2304.1
 ## Model Version(s):
 v1.0  <br>
 
-# Training, Testing, and Evaluation Datasets:
+## Training, Testing, and Evaluation Datasets:
 
-The data used to train this model contained synthetically-generated LLM poisoning attacks. <br>
+**Data Collection Method by Dataset:** <br>
+* Synthetic <br>
+* Hybrid: derived, open-source <br>
+
+**Labeling Method by Dataset:** <br>
+* Synthetic <br>
 
 ## Evaluation Benchmarks:
 Instruction-Data-Guard is evaluated based on two overarching criteria: <br>