思维链与自一致提示

使用 OpenAI API 的 Prompt Engineering

Fouad Trad

Machine Learning Engineer

思维链提示

要求大语言模型在作答前给出推理步骤（思路）
用于复杂推理任务
有助于降低模型错误

图示：思维链提示要求模型按步骤解题，输出包含每步的推理。

思维链提示

用标准提示解决推理任务

prompt = """Q: You start with 15 books in your collection. At the bookstore, you 
purchase 8 new books. Then, you lend 3 to your friend and 2 to your cousin. Later, 
you visit another bookstore and buy 5 more books. How many books do you have now? 
A: The answer is"""

print(get_response(prompt))

25 books

思维链提示

用思维链提示解决推理任务

prompt = """Q: You start with 15 books in your collection. At the bookstore, you 
purchase 8 new books. Then, you lend 3 to your friend and 2 to your cousin. Later, 
you visit another bookstore and buy 5 more books. How many books do you have now? 
A: Let's think step by step""" 
print(get_response(prompt))

Step 1: Start with the number of books in your collection: 15 books
Step 2: Purchase 8 new books at the bookstore: 15 + 8 = 23 books
Step 3: Lend 3 books to your friend: 23 - 3 = 20 books
Step 4: Lend 2 books to your cousin: 20 - 2 = 18 books
Step 5: Visit another bookstore and buy 5 more books: 18 + 5 = 23 books
Therefore, you have 23 books now.

少样本的思维链提示

example = """
Q: The odd numbers in this group add up to an even number:  9, 10, 13, 4, 2.
A: Adding all the odd numbers (9, 13) gives 22. The answer is True.
"""

question = """
Q: The odd numbers in this group add up to an even number: 15, 13, 82, 7. 
A:
"""

prompt = example + question
print(get_response(prompt))

Adding all the odd numbers (15, 13, 7) gives 35. The answer is False.

思维链 vs. 多步提示

多步提示

在提示中包含步骤

图示：多步提示为模型提供一系列按顺序执行的步骤。

思维链 vs. 多步提示

多步提示

在提示中包含步骤

图示：多步提示为模型提供一系列按顺序执行的步骤。

思维链提示

要求模型生成中间步骤

图示：在思维链提示中，模型在生成输出时产出各步骤。

思维链的局限

一次错误思路 -> 错误结果
引入了自一致提示

图示：思维链提示中，若某一步推理有误，会导致失败的结果。

自一致提示

多次提示模型以生成多条思维链
通过多数投票得到最终输出

图示：自一致提示通过多条思维链分别得到输出，最终用多数投票确定结果。

自一致提示

可通过定义多个提示，或一个可生成多个回答的提示来实现。

self_consistency_instruction = "Imagine three completely independent experts who 
reason differently are answering this question. The final answer is obtained by 
majority vote. The question is: "


problem_to_solve = "If there are 10 cars in the parking lot and 3 more cars arrive. 
Half the original number of cars leave. Then, half of the current number of cars 
arrive. How many cars are there in the parking?"


prompt = self_consistency_instruction + problem_to_solve

print(get_response(prompt))

自一致提示示例

Expert 1: Let's go step by step [...] Therefore, the total number of cars in the 
parking lot is 8 + 4 = 12.

Expert 2: First, let's calculate [...] Therefore, the total number of cars in the 
parking lot is now 5 + 2 = 7 cars.

Expert 3: Initially, there are 10 cars [...] Thus, the final answer is 8 + 4 = 12 
cars in the parking lot.

Based on the majority vote, the final answer is that there are 12 cars in the 
parking lot.

让我们练习！

使用 OpenAI API 的 Prompt Engineering