Learn Before
Improving Prompt Reliability with Delimiters
A user's prompt is failing to consistently extract a company name and sentiment from a piece of text because the model sometimes gets confused between the instructions and the text to be processed. The user's current prompt is: Extract the company name and sentiment from the following text. The service at Innovate Inc. was exceptional and I'm very happy. Rewrite this prompt using triple backticks (```) as delimiters to clearly separate the text to be analyzed from the instructions, thereby improving the model's reliability.
0
1
Tags
Ch.3 Prompting - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Application in Bloom's Taxonomy
Cognitive Psychology
Psychology
Social Science
Empirical Science
Science
Related
A user wants a language model to summarize a specific customer review. Their current prompt is:
Summarize the following customer review for me. The customer was initially unhappy with the shipping time but was very pleased with the product quality and customer service.The model's summary is often inaccurate because it gets confused about which part of the text is the instruction and which part is the review to be summarized. Which of the following revised prompts is most likely to produce the desired summary by most effectively clarifying the different parts of the input for the model?Debugging a Prompt for Text Summarization
Improving Prompt Reliability with Delimiters