SlideShare a Scribd company logo

Introduction to Prompt Engineering (Focusing on ChatGPT)

•
•
Chameera Dedduwage
Chameera Dedduwage

This is an introductory session on how to engineer prompts for commercially available Large Language Models (LLMs) such as ChatGPT and Gemini. This session uses ChatGPT as the example, but the strategies can be equally applied to Gemini and other LLMs.

1 of 26
Download to read offline
Introduction to Prompt Engineering CHAMEERA DEDDUWAGE MANAGER – DIGITAL STRATEGY B.SC., PG. DIP (APPLIED STATISTICS)
Most of us use ChatGPT and other LLMs for writing text. But it can do more. Writing ◦ Elaboration – expands an idea into a larger text. ◦ Summarisation - summarises a large text into a smaller text. Conceptualisation ◦ Ideation – lateral expansion of a text/idea based on similarities ◦ Extraction – extracting data, features, and information from a text. ◦ Transformation – transform data from one format to another. Entity-relations ◦ Classification – classifying entities based on given data. ◦ Relationships – find relationships between entities in a text.
Part I: Introduction to Prompts
What is a prompt? A prompt is a natural language request submitted to a language model to receive a response. Prompts can contain questions, instructions, contextual information, examples, and partial input for the model to complete or continue. After the model receives a prompt, depending on the type of model being used, it can generate text, embeddings, code, images, videos, music, and more.
What are the types of prompts? Input (required) ◦ Question ◦ Task ◦ Entity ◦ Completion Context (optional) Examples (optional)
Question-type inputs A question input is a question that you ask the model that the model provides an answer to. Example: What are the top 10 most travelled destinations in Asia?
Task inputs A task input is a task that you want the model to perform. For example, you can tell the model to give you ideas or suggestions for something. Example: Give me a list of steps (numbered) to travel from Paris to Moscow, using only public transport.
Entity inputs An entity input is what the model acts on, such as classifying or summarising. This type of input can benefit from the inclusion of instructions. Example: Classify the following items as [large, small]. Elephant Mouse Snail
Completion inputs A completion input is a text that the model is expected to complete or continue. Example: Some simple writing devices to use in fiction would be...
Context: an example Marbles: Color: red Number: 12 Color: blue Number: 28 Color: yellow Number: 15 Color: green Number: 17 How many green marbles are there?
Context: transformation E.g., Transform this data into JSON format.
Context: transformation E.g., Convert this to an unordered list in LaTex. Here's the JSON representationconverted into an unorderedlist in LaTeX format: begin{itemize} item textbf{Color:} red, textbf{Number:}12 item textbf{Color:} blue, textbf{Number:}28 item textbf{Color:} yellow, textbf{Number:}15 item textbf{Color:} green, textbf{Number:}17 end{itemize}
Part II: General Considerations
Clear definition of the task Example: Give me a paragraph arguing that Large Language Models can help humans discover new, unseen connections.
Applying constraints Example: This paragraph was a bit too long. Give me a 50-word paragraph.
Setting rules Example: Expand the above paragraph to a 100-word paragraph. The word "inevitable" must be there. Mark that word with a bold text.
Setting the tone Example: Rewrite the same paragraph in a playful tone.
Define the format Example: Transform the same to a bullet list. Preserve the tone.
Few-shot, one-shot, and zero-shot Example: Please choose the most verbose explanation from these two: Question: Why is sky blue? Explanation 1: The sky appears blue because of Rayleigh scattering, which causes shorter blue wavelengths of light to be scattered more easily than longer red wavelengths, making the sky look blue. Explanation 2: Due to the Rayleigh scattering effect.
Context, context, context… Example: Consider the following exchange: Ella: Being a woman is not cosplay. Betty: That's transphobic! Context:Ella is a natural-born female, hardcore Christian, and politically conservative, whereas Betty is an atheist trans-woman. Is Betty's exclamation justified?
Enforce selection (1) Example: What should I do to fix my disconnected wifi? The light on my Wifi router is yellow and blinking slowly.
Enforce selection (2)
Enforce selection (3) Example: Multiple choice problem: Which of the following options describes the book The Odyssey? Options: - thriller - sci-fi - mythology - biography
Prompt not just the content, but the format as well (1) Example: Create an outline for an essay about the history of Galle, Sri Lanka. I. Introduction *
Prompt not just the content, but the format as well (2) Example: At a particular food joint, an order can contain between 0-5 of the following: Ulundu Vadai, Masala Vadai, Alu Bonda, and Chai. A customer orders 2 Masala Vadai + a Chai. Display the order in JSON format. Display zero- volume items as well. Display as a copiable code block.
See you on next Monday. THAT’S IT FOR TODAY.

More Related Content

Introduction to Prompt Engineering (Focusing on ChatGPT)

  • 1. Introduction to Prompt Engineering CHAMEERA DEDDUWAGE MANAGER – DIGITAL STRATEGY B.SC., PG. DIP (APPLIED STATISTICS)
  • 2. Most of us use ChatGPT and other LLMs for writing text. But it can do more. Writing ◦ Elaboration – expands an idea into a larger text. ◦ Summarisation - summarises a large text into a smaller text. Conceptualisation ◦ Ideation – lateral expansion of a text/idea based on similarities ◦ Extraction – extracting data, features, and information from a text. ◦ Transformation – transform data from one format to another. Entity-relations ◦ Classification – classifying entities based on given data. ◦ Relationships – find relationships between entities in a text.
  • 3. Part I: Introduction to Prompts
  • 4. What is a prompt? A prompt is a natural language request submitted to a language model to receive a response. Prompts can contain questions, instructions, contextual information, examples, and partial input for the model to complete or continue. After the model receives a prompt, depending on the type of model being used, it can generate text, embeddings, code, images, videos, music, and more.
  • 5. What are the types of prompts? Input (required) ◦ Question ◦ Task ◦ Entity ◦ Completion Context (optional) Examples (optional)
  • 6. Question-type inputs A question input is a question that you ask the model that the model provides an answer to. Example: What are the top 10 most travelled destinations in Asia?
  • 7. Task inputs A task input is a task that you want the model to perform. For example, you can tell the model to give you ideas or suggestions for something. Example: Give me a list of steps (numbered) to travel from Paris to Moscow, using only public transport.
  • 8. Entity inputs An entity input is what the model acts on, such as classifying or summarising. This type of input can benefit from the inclusion of instructions. Example: Classify the following items as [large, small]. Elephant Mouse Snail
  • 9. Completion inputs A completion input is a text that the model is expected to complete or continue. Example: Some simple writing devices to use in fiction would be...
  • 10. Context: an example Marbles: Color: red Number: 12 Color: blue Number: 28 Color: yellow Number: 15 Color: green Number: 17 How many green marbles are there?
  • 12. Context: transformation E.g., Convert this to an unordered list in LaTex. Here's the JSON representationconverted into an unorderedlist in LaTeX format: begin{itemize} item textbf{Color:} red, textbf{Number:}12 item textbf{Color:} blue, textbf{Number:}28 item textbf{Color:} yellow, textbf{Number:}15 item textbf{Color:} green, textbf{Number:}17 end{itemize}
  • 14. Clear definition of the task Example: Give me a paragraph arguing that Large Language Models can help humans discover new, unseen connections.
  • 15. Applying constraints Example: This paragraph was a bit too long. Give me a 50-word paragraph.
  • 16. Setting rules Example: Expand the above paragraph to a 100-word paragraph. The word "inevitable" must be there. Mark that word with a bold text.
  • 17. Setting the tone Example: Rewrite the same paragraph in a playful tone.
  • 18. Define the format Example: Transform the same to a bullet list. Preserve the tone.
  • 19. Few-shot, one-shot, and zero-shot Example: Please choose the most verbose explanation from these two: Question: Why is sky blue? Explanation 1: The sky appears blue because of Rayleigh scattering, which causes shorter blue wavelengths of light to be scattered more easily than longer red wavelengths, making the sky look blue. Explanation 2: Due to the Rayleigh scattering effect.
  • 20. Context, context, context… Example: Consider the following exchange: Ella: Being a woman is not cosplay. Betty: That's transphobic! Context:Ella is a natural-born female, hardcore Christian, and politically conservative, whereas Betty is an atheist trans-woman. Is Betty's exclamation justified?
  • 21. Enforce selection (1) Example: What should I do to fix my disconnected wifi? The light on my Wifi router is yellow and blinking slowly.
  • 23. Enforce selection (3) Example: Multiple choice problem: Which of the following options describes the book The Odyssey? Options: - thriller - sci-fi - mythology - biography
  • 24. Prompt not just the content, but the format as well (1) Example: Create an outline for an essay about the history of Galle, Sri Lanka. I. Introduction *
  • 25. Prompt not just the content, but the format as well (2) Example: At a particular food joint, an order can contain between 0-5 of the following: Ulundu Vadai, Masala Vadai, Alu Bonda, and Chai. A customer orders 2 Masala Vadai + a Chai. Display the order in JSON format. Display zero- volume items as well. Display as a copiable code block.
  • 26. See you on next Monday. THAT’S IT FOR TODAY.