Use inner monologue or a sequence of queries to hide the model's reasoning process

For some applications, the reasoning process that a model uses to arrive at a final answer would be inappropriate to share with the user.

The idea of inner monologue is to instruct the model to put parts of the output that are meant to be hidden from the user into a structured format that makes parsing them easy.

「モデルの出力を構造化してパースを簡単にする」（アプリケーションでパースすればユーザからは隠せる）

systemの例

Enclose all your work for this step within triple quotes (""").

アプリケーションは3連引用符でパースすればよさそう

Alternatively, this can be achieved with a sequence of queries in which all except the last have their output hidden from the end user.

IMO：LangChainでプロンプトを連鎖させていくイメージ

First, we can ask the model to solve the problem on its own.

Next, we can have the model use all available information to assess the correctness of the student’s solution.

system

Compare your solution to the student's solution and evaluate if the student's solution is correct or not.

Finally, we can let the model use its own analysis to construct a reply in the persona of a helpful tutor.

NextやFinallyのプロンプトでは情報は重複させている