Naomibas/llm-system-prompts-benchmark

该数据集包含100个系统提示，用于测试大型语言模型的能力，包括遵循语法模式、回答选择题、模仿特定角色、记忆信息以及用法语交流。数据集的文件包括Python脚本和JSON文件，用于运行测试和显示提示。数据集由Naomi Bashkansky和Kenneth Li创建，主要用于研究目的，特别是用于比较不同模型或改进模型遵循系统提示的能力。

This dataset is a collection of 100 system prompts for large language models, designed to test a models ability to follow grammatical patterns, answer basic multiple choice questions, act according to a particular persona, memorize information, and speak in French. The dataset includes Python scripts and JSON files for running tests and displaying prompts. Created by Naomi Bashkansky and Kenneth Li, it is primarily intended for research purposes, especially for comparing different models or improving a models ability to follow system prompts.

原始信息汇总

数据集概述

该数据集包含100个系统提示，用于大型语言模型。