AI Something: The no BS everyday AI Newsletter
Posts
26 Prompting Tips - Prompt Principle for Instructions

26 Prompting Tips - Prompt Principle for Instructions

Discover 26 simple techniques to prompt better based on academic research.

January 28, 2024

Large language models (LLMs) like ChatGPT and Google Gemini have impressive problem-solving abilities across different domains and tasks, such as answering questions, code generations, and essay generations. To use AI effectively and enhance the quality of the response from trained LLms, there are various techniques, such as fine-tuning and RAG; however, the most essential and easy task is simply to curate better prompts.

In today’s rundown:

Targeted Audience: Prompt Engineers, Developers, and Daily AI users.
Why another prompt engineering article?
Summary of 26 prompt principles for LLMs instructions.

Read time: 4 minutes.

Why another article on prompt engineering?

Prompt Engineering is the art of communicating with any Large Language Models

ChatGPT

Monetization opportunities: There are many opportunities to earn some side money with prompt engineering: Ebook for prompts for your niche, prompt engineering courses. Using AI better will also help you excel in your daily jobs and further your career.
Get better at using AI. There is too much hype on AI tools that are described as “magic.” I want to emphasize that AI tools, despite being fancy and impressive, are only tools. Since AI will only become a more daily thing rather than a novel experience, it’s essential to understand the fundamentals. A fancy tool cannot make anything impressive itself without the user.
It’s a crime to find good resources and not share them.

26 Prompt Principles

Diagram of 26 prompt principles.

When communicating with LLM, it is not necessary to use polite phrases such as "please", "if you don't mind", "thank you" or "I would like to".”” It is recommended to be direct and concise in your communication to convey your message effectively.
Integrate the intended audience, assuming their expertise, into the prompt.
Break down complex tasks into a sequence of simpler prompts in an interactive conversation.
Employ affirmative directives such as ‘do’ while steering clear of negative language like ‘don’t.’
When you need clarity or a deeper understanding of a topic, idea, or any piece of information, utilize the following prompts: Explain [insert specific topic] in simple terms. Explain to me like I’m 11 years old. Explain to me as if I’m a beginner in [field]. Write the [essay/text/paragraph] using simple English like you’re explaining something to a 5-year-old.
Add “I’m going to tip $xxx for a better solution!”
Implement example-driven prompting (Use few-shot prompting).
When 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 input data.
Incorporate the following phrases: “Your task is” and “You MUST”. Be assertive with what you want.
Incorporate the following phrases: “You will be penalized”.
Use the phrase ”Answer a question given in a natural, human-like manner” in your prompts.
Use leading words like writing “think step by step.”
Add to your prompt the following phrase: “Ensure that your answer is unbiased and does not rely on stereotypes”.
Allow 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...”).
To 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.”
Assign a role to the large language models.
Use Delimiters.
Repeat a specific word or phrase multiple times within a prompt.
Combine Chain-of-thought (CoT) with few-shot prompts.
Use 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.
To 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.”
To correct/change specific text without changing its style: “Try to revise every paragraph sent by users. You should only improve the user’s grammar and vocabulary and make sure it sounds natural. You should not change the writing style, such as making a formal paragraph casual”.
When you have a complex coding prompt that may be in different files: “From now and on, whenever you generate code that spans more than one file, generate a [programming language ] script that can be run to automatically create the specified files or make changes to existing files to insert the generated code. [your question]”.
When 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.
Clearly state the requirements that the model must follow in order to produce content in the form of keywords, regulations, hints, or instructions.
To write any text, such as an essay or paragraph, that is intended to be similar to a provided sample, include the following instructions: Please use the same language based on the provided paragraph[/title/text /essay/answer].

🚀 That’s it! You have learned how to structure prompts better based on academic research.

The summary above is referenced from this research paper. If you find it interesting, please feel free to support their GitHub (not affiliated).

GitHub - VILA-Lab/ATLAS: A principled instruction benchmark on formulating effective queries and prompts for large language models (LLMs). Our paper: https://arxiv.org/abs/2312.16171

A principled instruction benchmark on formulating effective queries and prompts for large language models (LLMs). Our paper: https://arxiv.org/abs/2312.16171 - GitHub - VILA-Lab/ATLAS: A principled...

github.com/VILA-Lab/ATLAS

Give love to your favorite tools 💞

Vote for a chance to win a $20 gift card to contribute toward your favorite tools. Your choice will help others discover the emerging useful tool, and the winning tool will be crowned the AI overlord for the month.

Do you find this article helpful?

That’s a wrap! 🌯

I hope you will find the article helpful and can incorporate these instructions to better your output with AI.