Fix COT explanation to be decoded before the score #7
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Outdated suggestions cannot be applied.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.
@sayakpaul Really cool project. Just wanted to point out one minor issue.
Currently the score is placed before the explanation in the schema for each grader. As such, the LLM will generate the score before the explanation during decoding.
What you instead want is the explanation before the score. Cause, we want the model to generate its rationale/chain-of-thought and then arrive at the score during decoding. That helps with better grading.
If you generate the
score
before, the tokens forrationale
are simply post-hoc explanation for the score.Karpathy actually discusses this as well in his latest video here starting at timestamp
1:46:56
.Here is another article from someone who did statistical analysis to prove that the order matters, in case you are interested to dig deeper.