Enable regex to extract floats in score generation #1223
Merged
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
dosubot
bot
added
the
size:XS
sfc-gh-dhuang
requested review from
sfc-gh-dkurokawa,
sfc-gh-chu,
sfc-gh-jfishbein,
sfc-gh-pdharmana and
a team
sfc-gh-dhuang
force-pushed
the
fix-regex-floating-point
branch
from
092ea37
to
6d55f0a
Compare
dosubot
bot
added
size:S
sfc-gh-jreini
approved these changes
Jun 18, 2024
|
|
||
| vals = set() | ||
| for match in matches: | ||
| try: | ||
| vals.add(validate_rating(int(match))) | ||
| vals.add( | ||
| validate_rating(int(float(match))) |
There was a problem hiding this comment.
kinda late to the game, but:
- Why are we constrained to ints?
- If we are constrained to ints, shouldn't we round it instead of flooring it?
- The doc on L54 says "If the string does not match an integer ... raises an error ...", but this won't do that.
There was a problem hiding this comment.
- No particular reason beyond easier intrepretability for the end users AFAIK.
- Make sense - I can make a change to this
- Same as 1. - I do recall we went back and forth a bit on this and the doc just became outdated b/c of my change. Will update
Merged
sfc-gh-dhuang
added a commit
that referenced
this pull request
Jun 28, 2024
* match floats and integers for score generation * bb * updated expected test cases * minor fix
sfc-gh-dhuang
added a commit
that referenced
this pull request
Jul 1, 2024
* match floats and integers for score generation * bb * updated expected test cases * minor fix
sfc-gh-chu
pushed a commit
that referenced
this pull request
Sep 25, 2024
* match floats and integers for score generation * bb * updated expected test cases * minor fix
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.
Items to add to release announcement:
During benchmarking of various feedback providers, I notice there are models (i.e. a finetuned
mixtral-8x7bthat tend to give10.0instead of10in their feedback scoring before normalization. In the current implementation,PATTERN_INTEGERwill extract0and10from10.0and eventually pick the lesser value.Failing example when testing groundedness feedback functions - where the score accompanying COT was interpreted as
0, instead of the expected10:I'm switching to
PATTERN_NUMBERto unblock for now.Other details that are good to know but need not be announced:
PATTERN_INTEGERwas used overPATTERN_NUMBERin the previous PR. cc @sfc-gh-pmardziel to add more background if I'm missing sth obvious.I do believe we should move toward structured and systematic feedback score generation mechanisms with some self-refining prompt iterations (i.e. via DSPy) ASAP for more robust score generation, ideally before integrating w/ the monitoring stack, even at the cost of slightly higher token usage/cost/latency (which can also be alleviated via better prompts and instruction tuning).