Basics of Prompting

提示的基本知識

Basic Prompts

基本提示

You can achieve a lot with simple prompts, but the quality of results depends on how much information you provide it and how well-crafted it is. A prompt can contain information like the instruction or question you are passing to the model and including other details such as context, inputs, or examples. You can use these elements to instruct the model better and as a result get better results.

你可以透過簡單的提示實現很多，但結果的品質取決於你提供的資訊量和提示的精細程度。提示可以包含諸如傳遞給模型的“指令”或“問題”之類的資訊，以及其他細節，例如“上下文”、“輸入”或“示範”。你可以使用這些元素更好地指導模型，從而獲得更好的結果。

Let's get started by going over a basic example of a simple prompt:

讓我們開始透過簡單提示的基本示範。

Prompt

提示

The sky is

Output:

輸出:

blue

The sky is blue on a clear day. On a cloudy day, the sky may be gray or white.

As you can see, the language model outputs a continuation of strings that make sense give the context "The sky is". The output might be unexpected or far from the task we want to accomplish.

如您所見，語言模型輸出了一系列與上下文 "天空是" 相關的字串。輸出可能出乎意料或與我們想要完成的任務相距甚遠。

This basic example also highlights the necessity to provide more context or instructions on what specifically we want to achieve.

這個基本範例也凸顯了需要提供更多上下文或指示，以確切瞭解我們想要實現的目標。

Let's try to improve it a bit:

讓我們試著稍微改進它：

Prompt:

提示:

Complete the sentence:

The sky is

Output:

輸出:

so  beautiful today.

Is that better? Well, we told the model to complete the sentence so the result looks a lot better as it follows exactly what we told it to do ("complete the sentence"). This approach of designing optimal prompts to instruct the model to perform a task is what's referred to as prompt engineering.

那樣好一些嗎？我們告訴模型完成句子，所以結果看起來更好，因為它完全按照我們告訴它要做的事情（“完成句子”）進行。設計最佳提示以指示模型執行任務的方法被稱為提示工程。

The example above is a basic illustration of what's possible with LLMs today. Today's LLMs are able to perform all kinds of advanced tasks that range from text summarization to mathematical reasoning to code generation.

以上示範是LLMs今天所能實現的基本說明。今天的LLMs能夠執行各種進階任務，從文字摘要到數學推理到程式碼生成。

Prompt Formatting

提示格式化

We have tried a very simple prompt above. A standard prompt has the following format:

我們剛才使用了一個非常簡單的提示。標準提示的格式如下：

<Question>?

或

<Instruction>

This can be formatted into a question answering (QA) format, which is standard in a lot of QA datasets, as follows:

這可以格式化為問答（QA）格式，這在許多QA資料集中是標準的，如下所示：

Q: <Question>?
A:

When prompting like the above, it's also referred to as zero-shot prompting, i.e., you are directly prompting the model for a response without any examples or demonstrations about the task you want it to achieve. Some large language models do have the ability to perform zero-shot prompting but it depends on the complexity and knowledge of the task at hand.

當像上面那樣提示時，它也被稱為零樣本提示(zero-shot prompting)，即，您直接提示模型進行回應，而不需要任何有關您想要實現的任務的示範或示範。一些大型語言模型確實具有執行零樣本提示的能力，但這取決於手頭任務的複雜性和知識。

Given the standard format above, one popular and effective technique to prompting is referred to as few-shot prompting where we provide exemplars (i.e., demonstrations). Few-shot prompts can be formatted as follows:

鑑於上述的標準格式，一種流行且有效的提示技術被稱為少量樣本提示，其中我們提供範例（即示範）。少量樣本提示可以格式化如下：

<Question>?
<Answer>

<Question>?
<Answer>

<Question>?
<Answer>

<Question>?

The QA format version would look like this:

The QA格式版本將會長成這樣：

Q: <Question>?
A: <Answer>

Q: <Question>?
A: <Answer>

Q: <Question>?
A: <Answer>

Q: <Question>?
A:

Keep in mind that it's not required to use QA format. The prompt format depends on the task at hand. For instance, you can perform a simple classification task and give exemplars that demonstrate the task as follows:

請記住，並非必須使用QA格式。提示格式取決於手頭的任務。例如，您可以執行簡單的分類任務，並提供以下示範以示範該任務：

Prompt:

提示:

This is awesome! // Positive
This is bad! // Negative
Wow that movie was rad! // Positive
What a horrible show! //

Output:

輸出:

Negative

Few-shot prompts enable in-context learning which is the ability of language models to learn tasks given a few demonstrations.

Few-shot提示使上下文學習成為可能，即語言模型在給定少量示範的情況下學習任務的能力。

LLM Settings Prompt Elements