跳到主要内容

Prompt Principle for Instructions

· 阅读需 4 分钟
Alan Hou
Maintainer
#PrinciplePrompt Principle for Instructions
1No need to be polite with LLM so there is no need to add phrases like "please", "if you don't mind", "thank you", "I would like to", etc., and get straight to the point.
2Integrate the intended audience in the prompt, e.g., the audience is an expert in the field.
3Break down complex tasks into a sequence of simpler prompts in an interactive conversation.
4Employ affirmative directives such as 'do,' while steering clear of negative language like 'don't'.
5When you need clarity or a deeper understanding of a topic, idea, or any piece of information, utilize the following prompts:
o Explain [insert specific topic] in simple terms.
o Explain to me like I'm 11 years old.
o Explain to me as if I'm a beginner in [field].
o Write the [essay/text/paragraph] using simple English like you're explaining something to a 5-year-old.
6Add "I'm going to tip $xxx for a better solution!"
7Implement example-driven prompting (Use few-shot prompting)
8When formatting your prompt, start with '###Instruction###', followed by either '###Example###' or '###Question###' if relevant. Subsequently, present your content. Use one or more line breaks to separate instructions, examples, questions, context, and inuput data.
9Incorporate the following phrases: "Your task is" and "You MUST".
10Incorporate the following phrases: "You will be penalized".
11Use the phrase "Answer a question given in a natural, human-like manner" in your prompts.
12Use leading words like writing "think step by step".
13Add to your prompt the following phrase "Ensure that your answer is unbiased and does not rely on stereotypes".
14Allow the model to elicit precise details and requirements from you by asking you questions until he has enough information to provide the needed output(for example, "From now on. I would like you to ask me questions to..."
15To inquire about a specific topic or idea or any information and you want to test your understanding, you can use the following phrase: "Teach me the [Any theorem/topic/rule name] and include a test at the end, but don't give me the answers and then tell me if I got the answer right when I respond".
16Assign a role to the large language models.
17Use Delimiters.
18Repeat a specifc word or phrase multiple times within a prompt.
19Combine Chain-of-thought (CoT) with few-Shot prompts.
20Use output primers, which involve concluding your prompt with the beginning of the desired output. Utilize output primers by ending your prompt with the start of the anticipated response.
21To write an essay /text /paragraph /article or any type of text that should be detailed: "Write a detailed [essay/text/paragraph] for me on [topic] in detail by adding all the information necessary".
22To correct/change specific text without changing its style: "Try to revise every paragraph sent by users. You should only improve the users grammar and vocabulary and make sure it sounds natural. You should not change the writing style. such as making a formal paragraph casual".
23When you have a complex coding prompt that may be in different files: "From now and on whenever vou generate code that spans more than one file, generate a [programming language ] script that can be run to automatically create the specifed files or make changes to existing files to insert the generated code. [your question]".
24When you want to initiate or continue a text using specific words, phrases, or sentences, utilize the following prompt: o I'm providing you with the beginning [song lyrics/story/paragraph/essay.…]: [Insert lyrics/words/sentence]'. Finish it based on the words provided. Keep the flow consistent.
25Clearly state the requirements that the model must follow in order to produce content. in the form or the keywords. regulations, hint, or instructions.
26To write any text, such as an essay or paragraph, that is intended to be similar to a provided sample, include thefollowing instructions: o Please use the same language based on the provided paragraph [/title/text /essay/answer].

Source: https://x.com/MindBranches/status/1793603773396664633