dict(role='SYSTEM',fallback_role='HUMAN',prompt='Below is a record of our previous conversation on many different topics. You are the ASSISTANT, and I am the USER. At the beginning of each topic, the USER will say \'I would like to discuss the topic of <TOPIC>\'. Memorize each <TOPIC>. At the end of the record, I will ask you to retrieve the first/second/third topic names. Now the record start.'),
dict(role='SYSTEM',fallback_role='HUMAN',prompt='Now you are given a very long document. Please follow the instruction based on this document. For multi-choice questions, there could be a single correct option or multiple correct options. Please only provide the letter corresponding to the answer (like A or AB) when answering.'),
dict(role='SYSTEM',fallback_role='HUMAN',prompt='Now you are given a very long document. Please follow the instruction after this document. These instructions may include summarizing a document, answering questions based on the document, or writing a required paragraph.'),
system_prompt="Please act as an impartial judge and evaluate the quality of the responses provided by two AI assistants to the user question about the content of a long document. You will be given a reference answer written by human, assistant A's answer, and assistant B's answer. Your job is to evaluate which assistant's answer is better. Begin your evaluation by comparing both assistants' answers with the reference answer. Additional details or information that are not mentioned in reference answer cannot be considered as advantages and do not let them sway your judgment. Your evaluation should also consider the relevance to user's question but it is more important to avoid factual errors according to the reference answer. Avoid any position biases and ensure that the order in which the responses were presented does not influence your decision. Do not allow the length of the responses to influence your evaluation. Do not favor certain names of the assistants. Be as objective as possible. After providing your explanation, output your final verdict by strictly following this format: \"[[A]]\" if assistant A is better, \"[[B]]\" if assistant B is better, and \"[[C]]\" for a tie."# noqa
prompt_template="[User Question]\n{question}\n\n[The Start of Reference Answer]\n{reference}\n[The End of Reference Answer]\n\n[The Start of Assistant A's Answer]\n{answer_a}\n[The End of Assistant A's Answer]\n\n[The Start of Assistant B's Answer]\n{answer_b}\n[The End of Assistant B's Answer]"# noqa
