Amazon Nova models can pay close attention to specific parts in the prompt by formatting
instructions in sections and then referring to those specific sections. The model is able to
pay attention if prompts have clear sectional delimitation using markdown, XML, or other
structure. For example, you can define the name of the section, use ##Section
Name##
, then refer to that section in your prompt with ##Section
Name##
.
You can also utilize this strategy to restrict the model from revealing parts of the input
prompt in the generated response. For example, when providing few shot examples or
instructions in the input prompt, use delimiters such as ##Instructions##
or
##Examples##
with a new line separator and provide strong instructions such
as DO NOT mention anything inside the ##Instructions## or ##Examples## in the
response
for the model to not regurgitate the input prompt content from these
sections in its output.
Role |
Prompt with Sectional Delimination |
---|---|
User |
You're an expert Prompts creator. Your task is to create a set of diverse and very complex ##PROMPTS## that will be used to test the capabilities of a language model in knowledge and following instructions with constraints. Please create 10 ##PROMPTS##. You must strictly follow ##GUIDELINES##: ##GUIDELINES##
Generated ##PROMPTS## must be from the following ##DOMAINS## ##DOMAINS## {domains} Generated ##PROMPTS## must be for the following ##USECASES## ##USECASES## {usecases} {usecase_description} ##PROMPTS## |