抛弃普通思维链
Plan and Solve1 改进了零样本思维链（CoT）提示的使用，该提示为大型语言模型添加了更详细的指令。
Plan and Solve 提示
[用户提示]
让我们首先理解问题，提取相关变量及其对应的数值，并制定完整的计划。然后，让我们执行计划，计算中间变量（注意正确的数值计算和常识），逐步解决问题，并显示答案。
[模型响应]
因此答案（阿拉伯数字）是
这是一个两步过程，指导 LLM 更关注计算和中间结果，以尽可能确保其正确执行。
- 生成推理：在第一步中，我们使用用户查询提示模型，并使用 plan and solve 提示预热模型，以便在生成中间推理过程之前明确制定解决问题的计划。
- 提取答案：一旦获得模型的推理，我们就会从包含模型思维链的新提示中提取答案。
我们可以使用 instructor 来实现这一点，如下所示。
import instructor
from openai import OpenAI
from pydantic import BaseModel
client = instructor.from_openai(OpenAI())
class Reasoning(BaseModel):
chain_of_thought: str
class Response(BaseModel):
correct_answer: str
def generate_reasoning(query: str):
return client.chat.completions.create(
messages=[
{
"role": "user",
"content": f"""
<user query>
{query}
</user query>
Let's first understand the problem,
extract relevant variables and their
corresponding numerals, and make a
complete plan. Then, let's carry out
the plan, calculate intermediate
variables (pay attention to correct
numerical calculation and commonsense),
solve the problem step by step, and
show the answer.
""",
},
],
response_model=Reasoning,
model="gpt-4o",
)
def extract_answer(query: str, reasoning: Reasoning):
return client.chat.completions.create(
messages=[
{
"role": "user",
"content": f"""
<user query>
{query}
</user query>
Let's first understand the problem,
extract relevant variables and their
corresponding numerals, and make a
complete plan. Then, let's carry out
the plan, calculate intermediate
variables (pay attention to correct
numerical calculation and commonsense),
solve the problem step by step, and
show the answer.
<reasoning>
{reasoning.chain_of_thought}
</reasoning>
Therefore the answer (arabic numerals) is
""",
}
],
model="gpt-4o",
response_model=Response,
)
if __name__ == "__main__":
query = (
"In a dance class of 20 students, 20% enrolled "
"in contemporary dance, 25% of the remaining "
"enrolled in jazz dance and the rest enrolled "
"in hip-hop dance. What percentage of the entire "
"students enrolled in hip-hop dance?"
)
reasoning = generate_reasoning(query)
print(reasoning.model_dump_json(indent=2))
"""
{
"chain_of_thought": "Let's first break down the
problem:\n\n1. Total number of students = 20\n2.
Percentage enrolled in contemporary dance = 20%\n\n
Step-by-Step Plan:\n1. Calculate the number of
students enrolled in contemporary dance.\n2.
Calculate the remaining students after contemporary
dance enrollment.\n3. Calculate the percentage and
number of students from the remaining who enrolled in
jazz dance.\n4. Determine the remaining students who
enrolled in hip-hop dance.\n5. Finally, calculate the
percentage of the entire students who enrolled in
hip-hop dance.\n\nLet's carry out the plan:\n\n1.
Number of students enrolled in contemporary dance =
20% of 20 = (20/100) * 20 = 4\n2. Remaining students
after contemporary = 20 - 4 = 16\n3. Percentage of
remaining students enrolled in jazz dance = 25%\n
Number of students enrolled in jazz dance = 25% of 16
= (25/100) * 16 = 4\n4. Remaining students after
contemporary and jazz = 16 - 4 = 12\n5. The number of
students enrolled in hip-hop dance = 12\n6.
Percentage of entire students enrolled in hip-hop =
(Number of hip-hop students / Total students) *
100\n Percentage = (12 / 20) * 100 = 60%\n\nThus,
60% of the entire students enrolled in hip-hop dance."
}
"""
response = extract_answer(query, reasoning)
print(response.model_dump_json(indent=2))
"""
{
"correct_answer": "60"
}
"""