Update README.md

README.md

@@ -32,11 +32,9 @@ Built with [PyTorch Lightning](https://www.pytorchlightning.ai/), this implement
 Each input sample is formatted as follows:
 
 ```
-truefalse: [MASK or answer] passage: [passage] </s>
+truefalse: [answer] passage: [passage] </s>
 ```
 
-During training, the answer is occasionally replaced with the `[MASK]` token (controlled by a defined masking probability). This strategy encourages the model to learn both to predict the answer and to generate a corresponding question.
-
 ### Target Construction
 
 Each target sample is formatted as:
@@ -68,8 +66,6 @@ The model’s performance was evaluated using BLEU scores for both the generated
 | BLEU-3  | 0.3089   |
 | BLEU-4  | 0.2431   |
 
-Additionally, the answer generation performance is notably strong, achieving a **BLEU-1 score of 90**.
-
 *Note: These metrics offer a quantitative assessment of the model’s quality in generating coherent and relevant question-answer pairs.*
 
 ## How to Use
@@ -82,9 +78,7 @@ from transformers import pipeline
 generator = pipeline("text2text-generation", model="Fares7elsadek/boolq-t5-base-question-generation")
 
 # Example inference:
-input_text = "truefalse: [MASK] passage: [Your passage here] </s>"
-# Alternatively, specify an answer directly:
-# input_text = "truefalse: yes passage: [Your passage here] </s>"
+input_text = "truefalse: [answer] passage: [Your passage here] </s>"
 result = generator(input_text)
 print(result)
 ```