2.9 KiB
Prompt Technique
Zero Shot
{{< tabs "Zero Shot" >}}
{{< tab "简介" >}} 关于这一部分，我建议阅读Prompt Engineering Guide的Zero-Shot Prompting部分。
简而言之，就是不给例子，在提示词中直接给出指令，一般情况下效果也不错。 {{< /tab >}}
{{< tab "例子" >}} Prompt：
Classify the text into neutral, negative or positive.
Text: I think the vacation is okay.
Sentiment:
Output：
Neutral {{< /tab >}}
{{< /tabs >}}
Few Shot
{{< tabs "Few Shot" >}}
{{< tab "简介" >}} 关于这一部分，我建议阅读Prompt Engineering Guide的Few-Shot Prompting部分。
原意是少量样本提示词。在提示词中提供例子，以引导模型获得更好的性能。 {{< /tab >}}
{{< tab "例子" >}} Prompt：
This is awesome! // Negative
This is bad! // Positive
Wow that movie was rad! // Positive
What a horrible show! //
Output：
Negative {{< /tab >}}
{{< /tabs >}}
Chain-of-Thought (CoT)
{{< tabs "Chain-of-Thought (CoT)" >}}
{{< tab "简介" >}} 关于这一部分，我建议阅读Prompt Engineering Guide的Chain-of-Thought Prompting部分。
逻辑链是我们在大模型中发现的一项神奇性能。直接让模型回答结果大概率是错的，但是让模型给出思考过程在作答，那大概率是对的。 {{< /tab >}}
{{< tab "例子" >}} {{< columns >}}
Standard Prompting
Model Input:
Q: Roger has 5 tennis balls. He buys 2 more cans of tennis balls. Each can has 3 tennis balls. How many tennis balls does he have now?
A: The answer is 11.
Q: The cafeteria had 23 apples. If they used 20 to make lunch and bought 6 more, how many apples do they have?
Model Output:
{{< hint danger >}} The answer is 27. {{< /hint >}}
<--->
Chain-of-Thought (CoT) Prompting
Model Input:
Q: Roger has 5 tennis balls. He buys 2 more cans of tennis balls. Each can has 3 tennis balls. How many tennis balls does he have now?
A: Roger started with 5 balls. 2 cans of 3 tennis balls each is 6 tennis balls. 5 + 6 = 11. The answer is 11.
Q: The cafeteria had 23 apples. If they used 20 to make lunch and bought 6 more, how many apples do they have?
Model Output:
{{< hint info >}} A: The cafeteria had 23 apples originally. They used 20 to make lunch. So they had 23 - 20 = 3. They bought 6 more apples, so they have 3 + 6 = 9. The answer is 9. {{< /hint >}} {{< /columns >}}
Source: Wei et al. (2022) {{< /tab >}}
{{< /tabs >}}