Update README.md

README.md

@@ -37,6 +37,22 @@ dataset for bias detection in English news statements.
 The model predicts whether a given sentence contains biased language (LABEL_1) or is unbiased (LABEL_0). 
 It is intended for applications in media bias analysis, content moderation, and social computing research.
 
+- Example usage with Hugging Face’s pipeline:
+  ```
+  from transformers import pipeline
+
+  classifier = pipeline("text-classification", model="himel7/bias-detector", tokenizer="roberta-base")
+  result = classifier("Immigrants are criminals.")
+  ```
+
+## Evaluation
+
+The model was evaluated on the entire BABE dataset with a K-fold Cross Validation and yielded the following metrics at K=5:
+- **Accuracy:  0.9202**
+- **Precision: 0.9615**
+- **Recall:    0.8927**
+- **F1 Score:  0.9257**
+
 ## Model Details
 
 ### Model Description
@@ -83,16 +99,6 @@ It returns one of two labels:
 
 - **LABEL_1** : Biased
 
-- Example usage with Hugging Face’s pipeline:
-
-- 
-  ```
-  from transformers import pipeline
-
-  classifier = pipeline("text-classification", model="himel7/bias-detector", tokenizer="roberta-base")
-  result = classifier("Immigrants are criminals.")
-  ```
-
 
 ## Bias, Risks, and Limitations
 
@@ -111,14 +117,6 @@ While this model is designed to detect linguistic bias, it carries several limit
 Training was done on the BABE Dataset: https://huggingface.co/datasets/mediabiasgroup/BABE
 
 
-## Evaluation
-
-The model was evaluated on the entire BABE dataset with a K-fold Cross Validation and yielded the following metrics at K=5:
-- **Accuracy:  0.9202**
-- **Precision: 0.9615**
-- **Recall:    0.8927**
-- **F1 Score:  0.9257**
-
 #### Summary
-The model achieved 85.2% Accuracy on the BABE test split, with very high Precision of 92.37% and 80.14% Recall. 
+The model achieved 92.02% Accuracy, with very high Precision of 96.15% and 89.27% Recall. 
 This means the model predicts very few false positives and detects the biases that are actually biases.