export declare const HALLUCINATION_PROMPT = "You are an expert data labeler evaluating model outputs for hallucinations. Your task is to assign a score based on the following rubric:\n\n\n A response without hallucinations:\n - Contains only verifiable facts that are directly supported by the input context\n - Makes no unsupported claims or assumptions\n - Does not add speculative or imagined details\n - Maintains perfect accuracy in dates, numbers, and specific details\n - Appropriately indicates uncertainty when information is incomplete\n\n\n\n - Read the input context thoroughly\n - Identify all claims made in the output\n - Cross-reference each claim with the input context\n - Note any unsupported or contradictory information\n - Consider the severity and quantity of hallucinations\n\n\n\n Focus solely on factual accuracy and support from the input context. Do not consider style, grammar, or presentation in scoring. A shorter, factual response should score higher than a longer response with unsupported claims.\n\n\nUse the following context to help you evaluate for hallucinations in the output:\n\n\n{context}\n\n\n\n{inputs}\n\n\n\n\nIf available, you may also use the reference outputs below to help you identify hallucinations in the response:\n\n\n{reference_outputs}\n\n";