Fixing LitQAEvaluation bugs: incorrect reward indices, not using LLM's native knowledge
#708
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
jamesbraza
requested review from
whitead,
sidnarayanan,
mskarlin,
maykcaldas and
nadolskit
dosubot
bot
added
the
size:L
mskarlin
reviewed
Nov 19, 2024
Comment on lines
101
to
104
| "Extract the single letter answer from the following question and answer" | ||
| "\n\n{qa_prompt}" | ||
| "\n\n{qa_answer}" | ||
| "\n\nQuestion: {qa_prompt}" | ||
| "\n\nAnswer: {qa_answer}" | ||
| "\n\nSingle Letter Answer:" |
There was a problem hiding this comment.
I'd suggest something like:
"Given the following question and a proposed answer to the question, return the single-letter choice that matches the proposed answer."
"\n\nQuestion: ..."
"\n\nProposed Answer: ..."
If I didn't know the context of this method, as a human, I'd find the original prompt unclear.
There was a problem hiding this comment.
Yeah it's a nice suggestion, but making this change breaks two of our test cases. Let's save this for another PR
There was a problem hiding this comment.
Incorporated into #724
jamesbraza
force-pushed
the
fixing-answer-incorrect
branch
from
35b33db to
65c97e3
Compare
mskarlin
approved these changes
Nov 19, 2024
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Outdated suggestions cannot be applied.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.
This PR:
EVAL_PROMPT_TEMPLATEdiscounted_returnslogic and incorrect reward indicesdiscounted_returnsand theTaskDatasetdistractorsbe aSequenceto avoid in-place edits, further robust-ification after Making sure we copy distractors #694Closes #693