metrum-ai/manipulation-resistant-prompts-96-96

这是一个包含特定目标词数的提示和目标输出的数据集，旨在测试和评估满足不同长度要求的语言模型。数据集使用词数作为衡量文本长度的标准，而不是token数，以反映现实世界中文本生成的实际情况。数据集包含了782个提示，每个提示和目标输出的目标长度均为96个词。

This dataset contains prompts with specified target word counts for both input prompts and target outputs, designed to test and evaluate language models across different length requirements. The dataset uses word counts as a measure of text length, reflecting real-world text generation scenarios. It includes 782 prompts, each with a target length of 96 words for both the prompt and the target output.