Prompt fix for empty intermediate steps in summarization #660
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Adding space before {text} and quotation marks around it avoids generating empty responses from OpenAI davinci-003. Empty responses in summarization messes up the final result or makes it very inaccurate.
The error from OpenAI would be: "The model predicted a completion that begins with a stop sequence, resulting in no output. Consider adjusting your prompt or stop sequences."
This fix corrects the prompting for summarization chain. Can be applied for other prompts too.
Same as for map_reduce (see commit commentary).
Same as for map_reduce prompting (see commit commentary).
Removed the space before \n\n"{text}" as it turns out it is not needed for correct response.
Removed the space before \n\n"{text}" as it turns out it is not needed for correct response.
Removed the space before \n\n"{text}" as it turns out it is not needed for correct response.
hwchase17
approved these changes
Jan 20, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Adding quotation marks around {text} avoids generating empty or completely random responses from OpenAI davinci-003. Empty or completely unrelated intermediate responses in summarization messes up the final result or makes it very inaccurate.
The error from OpenAI would be: "The model predicted a completion that begins with a stop sequence, resulting in no output. Consider adjusting your prompt or stop sequences."
This fix corrects the prompting for summarization chain. This works on API too, the images are for demonstrative purposes.
This approach can be applied to other similar prompts too.
Examples:
Without quotation marks
With quotation marks
