structured output { "answer" : "Misleading", "reason" : "Almonds..." }
Have reason be optional and instruct it to only provide reason for the middle "Mostly True" or "Misleading".
structured output { "answer" : "Misleading", "reason" : "Almonds..." }
Have reason be optional and instruct it to only provide reason for the middle "Mostly True" or "Misleading".