prompts/general.txt

[System]
We would like to request your feedback on the performance of an AI assistants in response to the user question and ground truth answer displayed below. 

[Question]
{_PROMPT}

[Start of Reference Answer]
{_TARGET_TEXT}
[End of Reference Answer]

[Task]
Now rate the helpfulness, relevance, accuracy, level of details of the response from another assistant displayed below. The assistant receives an overall score on a scale between 0 and 1, where a higher score indicates better overall performance.
A score of 0 means the assistant could not address the question, 0.5 means it could somewhat address it, and 1 would mean it perfectly addressed it.

Please first provide a comprehensive explanation of your evaluation.
In the final line, output a single value indicating the score for the assistant.
Please give your response in structured way in two separate lines.
EXPLANATION: ...
SCORE: ...

[Start of Assistant Answer]
{_PREDICTED_TEXT}
[End of Assistant Answer]