chatGPT究极进化指南-如何让prompt成为高效的咒语

chatGPT究极进化指南⸺如何让prompt成为高效的咒语
更多chatGPT知识：
0基础小白学习ChatGPT

来源⻚面：https://github.com/dair-ai/Prompt-Engineering-Guide
本文在线地址（可根据目录查看）：chatGPT究极进化指南⸺如何让prompt成为高效的咒语

翻译：openai
校对：Stephen（水平有限）
账号，plus代充，聊天机器人部署，chatGPT商业化交流微信：isiuonk
Prompting
Introduction（prompt介绍）
=====================================================================================
Prompt
engineering
is
a
relatively
new
discipline
for
developing
and
optimizing
prompts
to
efficiently
use
language
models
(LMs)
for
a
wide
variety
of
applications
and
research
topics.
Prompt
engineering
skills
help
to
better
understand
the
capabilities
and
limitations
of
large
language
models
(LLMs).
Researchers
use
prompt
engineering
to
improve
the
capacity
of
LLMs
on
a
wide
range
of
common
and
complex
tasks
such
as
question
answering
and
arithmetic
reasoning.
Developers
use
prompt
engineering
to
design
robust
and
effective
prompting
techniques
that
interface
with
LLMs
and
other
tools.
"提示工程是一⻔相对较新的学科，用于开发和优化提示以有效地使用语言模型（LMs）来处理各种应用程序和研究主题。提示工程技能有助于更好地了解大型语言模型（LLMs）的能力和局限性。研究人员使用提示工程来改进
LLMs
在各种常⻅和复杂的任务上的能力，例如问答和算术推理。开发者使用提示工程来设计强大而有效的提示技术，与
LLMs
和其他工具进行交互。"
This
guide
covers
the
basics
of
standard
prompts
to
provide
a
rough
idea
on
how
to
use
prompts
to
interact
and
instruct
large
language
models
(LLMs).
这篇指南涵盖了标准提示的基础知识，提供了使用提示与大型语言模型（LLMs）进行交互和指导的大致思路。All
examples
are
tested
with
text-davinci-003
(using
OpenAI's
playground)
unless
otherwise
specified.
It
uses
the
default
configurations,
e.g.,
temperature=0.7
and
top-p=1.
除非另有说明，否则所有例子都是使用
OpenAI
的
playground
中的
text-davinci-003
进行测试的。它使用默认配置，例如
temperature=0.7
和
top-p=1。
Topic:
•

[Basic
Prompts]





•

[A
Word
on
LLM
Settings]




•

[Standard
Prompts]





•

[Prompt
Elements]





•

[General
Tips
for
Designing
Prompts]





Basic
Prompts（基本提示）
---------------------------------------
You
can
already
achieve
a
lot
with
prompts,
but
the
quality
of
results
depends
on
how
much
information
you
provide
it.
A
prompt
can
contain
information
like
the
instruction
or
question
you
are
passing
to
the
model
and
including
other
details
such
as
inputs
or
examples.
你已经可以通过提示实现很多功能，但是结果的质量取决于你提供的信息量。提示可以包含如指令或问题等传递给模型的信息，以及包括其他细节，如输入或示例。Here
is
a
basic
example
of
a
simple
prompt:
这里是一个简单提示的基本例子：Prompt
The sky is天空是。123Output:
blueThe sky is blue on a clear day. On a cloudy day, the sky may be gray or white.在晴朗的日子里，天空是蓝色的。在多云的日子里，天空可能是灰色或白色的。12345As
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.
正如你所看到的，语言模型输出了一系列字符串的延续，这些字符串在给定上下文
“天空是......”
下是有意义的。输出结果可能出乎意料，或者离我们想要完成的任务相差甚远。This
basic
example
also
highlights
the
necessity
to
provide
more
context
or
instructions
on
what
specifically
we
want
to
achieve.
这个基本示例也突显了提供更多上下文或说明以明确我们想要实现的具体目标的必要性。Let's
try
to
improve
it
a
bit:
让我们试着稍微改进一下吧：Prompt:Complete the sentence: The sky is完成这个句子：天空12345Output:
so beautiful today.今天真美丽。123Is
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.
这个更好了吗？我们告诉模型要完成这个句子，所以结果看起来更好，因为它完全按照我们告诉它要做的
("完成句子")
来执行。这种通过设计最佳提示来指导模型执行任务的方法被称为提示工程。
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.
上面的例子是展示
LLMs
今天所能做到的基本示例。现今的
LLMs
能够执行各种高级任务，包括文本摘要、数学推理以及代码生成。A
Word
on
LLM
Settings（LLM
设置注意事项）
-----------------------------------------------------------------
When
working
with
prompts,
you
will
be
interacting
with
the
LLM
via
an
API
or
directly.
You
can
configure
a
few
parameters
to
get
different
results
for
your
prompts.
在使用提示时，您将通过
API
或直接与
LLM
进行交互。您可以配置一些参数，以获取不同的提示结果。Temperature
-
In
short,
the
lower
the
temperature
the
more
deterministic
the
results
in
the
sense
that
the
highest
probable
next
token
is
always
picked.
Increasing
temperature
could
lead
to
more
randomness
encouraging
more
diverse
or
creative
outputs.
We
are
essentially
increasing
the
weights
of
the
other
possible
tokens.
In
terms
of
application,
we
might
want
to
use
lower
temperature
for
something
like
fact-based
QA
to
encourage
more
factual
and
concise
responses.
For
poem
generation
or
other
creative
tasks
it
might
be
beneficial
to
increase
temperature.
温度
-
简而言之，温度越低，结果越确定，因为最有可能的下一个标记总是被优先选择。增加温度可能会导致更多的随机性，鼓励更多的多样化或创造性输出，实际上增加了其他可能标记的权重。在应用方面，对于像基于事实的问答这样的内容，我们可能希望使用较低的温度来鼓励更加实际和简洁的回答。对于诗歌生成或其他创意任务，增加温度可能会更有益。Top_p
-
Similarly,
with
top_p,
a
sampling
technique
with
temperature
called
nucleus
sampling,
you
can
control
how
deterministic
the
model
is
at
generating
a
response.
If
you
are
looking
for
exact
and
factual
answers
keep
this
low.
If
you
are
looking
for
more
diverse
responses,
increase
to
a
higher
value.
使用
top_p
技术和称为核心采样的带有温