Add multi-turn self-refine for entity relationship extractor #73
+570
−58
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
…le, need to update unittests and add notebooks
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Outdated suggestions cannot be applied.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.
Description
One-pass of the input text may not always return the full entities and relationships, so we can ask the LLM to refine its response via critique. The tradeoff for quality is to call the LLM several times more (perhaps parts of this can be substituted with distilled HF models in the future).
Here's a basic version that intends to improve mathematical solutions over multiple turns via critique:
https://github.com/NumberChiffre/mcts-llm/blob/main/mcts_llm/mctsr.py#L36-L86
We'd have to make sure the refined entities and relationships are unique each.