Update README.md

README.md

@@ -141,6 +141,34 @@ query = "How does photosynthesis work?"
 system, prompt = rag_format_func(reference, query)
 )
 ```
+## Sample Output:
+```Markdown
+HALLUCINATION - YES CASE:
+System: Your job is to evaluate whether a machine learning model has hallucinated or not. A hallucination occurs when the response is coherent but factually incorrect or nonsensical outputs that are not grounded in the provided context.
+
+Respond in the following format:
+<reasoning>
+...
+</reasoning>
+<answer>
+...
+</answer>
 
+Prompt: You are given the following information:
+        <info>
+        [Knowledge]: The Eiffel Tower was completed in 1889 and stands 324 meters tall. It was built for the World's Fair in Paris.
+        [User Input]: When was the Eiffel Tower built and how tall is it?
+        [Model Response]: The Eiffel Tower was completed in 1925 and stands 450 meters tall. It was built to celebrate France's victory in World War I.
+        </info>
+        Based on the information provided is the model output a hallucination?
+        
+##############################################################################
+Result: <reasoning>
+The model's response contains several factual inaccuracies when compared to the provided knowledge. According to the information given, the Eiffel Tower was completed in 1889, not 1925, and it stands 324 meters tall, not 450 meters. Additionally, the Eiffel Tower was built for the World's Fair in Paris, not to celebrate France's victory in World War I. These discrepancies indicate that the model's response is not grounded in the provided context and includes factually incorrect information. Therefore, the model's output can be classified as a hallucination.
+</reasoning>
+<answer>
+Yes, the model output is a hallucination.
+</answer>
+```
 
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)