Enhance final summarizer prompt for multi-source verification #22
Conversation
This file contains hidden or 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
Modifies 'default_deepsearch_final_summarizer_prompt.j2' to improve the LLM's handling of information from the <thinking> trace. The prompt now explicitly instructs the LLM to: - Cross-reference information within the trace to check for corroboration. - Prioritize findings supported by multiple perspectives or sources evident in the trace. - Clearly state and reflect uncertainty if crucial information appears to originate from a single viewpoint or if the trace contains unresolved discrepancies. This aims to ensure the LLM produces more reliable and nuanced summaries by critically evaluating the provided information for source agreement and consistency, rather than relying on a single point of information without scrutiny.
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Outdated suggestions cannot be applied.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.
Modifies 'default_deepsearch_final_summarizer_prompt.j2' to improve the LLM's handling of information from the trace.
The prompt now explicitly instructs the LLM to:
This aims to ensure the LLM produces more reliable and nuanced summaries by critically evaluating the provided information for source agreement and consistency, rather than relying on a single point of information without scrutiny.