Structuring Data
One simple and exciting use case for LLMs is organizing data into tables. Perhaps you have a bunch of news articles or business reports, and you would like all of the important points to be summarized in a table that you can then put into a spreadsheet or database. Chat bots like ChatGPT can help you do this.
We can extract information from the following report by appending Generate a table containing this information:
to it.
In a recent business report presentation, the CEO of Zana Corp. highlighted their remarkable growth in the past fiscal year. She shared that the company experienced a 15% increase in revenue, reaching $50 million, with a 12% profit margin ($6 million in net profit). The report also showcased a 20% growth in their customer base, now totaling 100,000 customers. Additionally, the company's operating expenses went up by 10%, amounting to $10 million, while the employee headcount increased by 25%, resulting in a current workforce of 500 employees.
Generate a table containing this information:
ChatGPT will output a table like the following:
Metric | Value |
---|---|
Revenue | $50 million |
Profit Margin | 12% |
Net Profit | $6 million |
Customer Base | 100,000 |
Operating Expenses | $10 million |
Employee Headcount | 500 |
Revenue Increase | 15% |
Customer Increase | 20% |
Operating Expenses Increase | 10% |
Employee Headcount Increase | 25% |
You can then copy and paste it into a spreadsheet like Excel/Sheets or even documents and powerpoints.
Sander Schulhoff
Sander Schulhoff is the CEO of HackAPrompt and Learn Prompting. He created the first Prompt Engineering guide on the internet, two months before ChatGPT was released, which has taught 3 million people how to prompt ChatGPT. He also partnered with OpenAI to run the first AI Red Teaming competition, HackAPrompt, which was 2x larger than the White House's subsequent AI Red Teaming competition. Today, HackAPrompt partners with the Frontier AI labs to produce research that makes their models more secure. Sander's background is in Natural Language Processing and deep reinforcement learning. He recently led the team behind The Prompt Report, the most comprehensive study of prompt engineering ever done. This 76-page survey, co-authored with OpenAI, Microsoft, Google, Princeton, Stanford, and other leading institutions, analyzed 1,500+ academic papers and covered 200+ prompting techniques.