26 Principles to Boost LLMs Responses by 50%

A recent study from Mohamed bin Zayed University of AI (MBZUAI) presents 26 principles to enhance prompt engineering for Large Language Models (LLMs). These principles are designed to optimize interaction with various LLM scales, including LLaMA-1/2 (7B, 13B, 70B) and GPT-3.5/4, focusing on aspects like prompt structure, clarity, and task specificity. Notable findings include an average 50% improvement in response quality and accuracy across different LLMs. 

The study emphasizes concise, context-relevant, and task-aligned prompts, advocating for incremental prompting and programming-like logic for complex tasks. It also highlights the importance of avoiding biases and adapting prompts based on model performance and human feedback.

The principles were tested using a benchmark called ATLAS, involving a diverse array of queries. While effective across the tested models, the study acknowledges limitations in handling highly complex or specialized questions, suggesting the need for future research to expand and refine these principles.

Here are the first 10 principles you can use:

1. No 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. 
   
2. Integrate the intended audience in the prompt, e.g., the audience is an expert in the field. 
   
3. Break down complex tasks into a sequence of simpler prompts in an interactive conversation. 
   
4. Employ affirmative directives such as ‘do,’ while steering clear of negative language like ‘don’t’. 
   
5. When 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.
   
6. Add “I’m going to tip $xxx for a better solution!”
   
7. Implement example-driven prompting (Use few-shot prompting).
   
8. 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.
   
9. Incorporate the following phrases: “Your task is” and “You MUST”.
10. Incorporate the following phrases: “You will be penalized”.