🟢 介绍
本章介绍如何使补全结果更加可靠，以及如何通过检查来确保补全结果的可靠性。
🟢 提示去偏差
本页面介绍了一些简单的技巧用以去除提示中的偏差。
🟡 Prompt Ensembling
Prompt ensembling is the concept of using multiple different prompts to try to
🟡 大语言模型自我评估
基本自我评估
🔴 校准大语言模型
通过校准输出分布(@zhao2021calibrate)，可以抵消LLM表现出的某些偏差。
🟡 Math
Throughout this course, we have seen many different prompting methods that can be used to improve %%LLM|LLM%% math ability. One recent approach, MathPrompter(@imani2023mathprompter), unifies some of these methods (%%CoT|CoT prompting%%, %%PAL|PAL%%, etc.) into a single technique. The overarching idea is to break down a math question into algebraic terms then use Python code to solve it in different ways.