Meta-eval: (4/7) Register ranking metrics as the meta-eval scoring adapter - #104
Open
ErlisLushtaku wants to merge 2 commits into
Open
Meta-eval: (4/7) Register ranking metrics as the meta-eval scoring adapter#104ErlisLushtaku wants to merge 2 commits into
ErlisLushtaku wants to merge 2 commits into
Conversation
The packaged task now declares scoring.adapter: ranking. That scorer fits Bradley-Terry on the forward-order rows and reports Spearman correlation and Elo MAE, split into English vs multilingual, matching the reference language table. Human ties are dropped from those splits by default; --meta_eval.include_human_ties keeps them.
This was referenced Aug 15, 2026
# Conflicts: # README.md
ErlisLushtaku
changed the title
ErlisLushtaku
marked this pull request as ready for review
August 17, 2026 09:21
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Note
Packaged meta-eval split from closed PR #76. Meta-eval does not use the unified
do_inferencecache, and the cache stack (#94-#100) does not wire it up either: caching will be added to meta-eval once those PRs are merged.Adds Bradley-Terry Spearman and Elo MAE, plus English vs multilingual splits, as the packaged
rankingscoring adapter. Language splits drop human ties by default. Ranking fits use one forward-order row per sampled battle.This is stacked on #103.