Add Turkish proverbs eval#1649
Open
kayametehan wants to merge 1 commit intoopenai:mainfrom
Open
Conversation
kayametehan
requested review from
andrew-openai,
etr2460 and
katyhshi
as code owners
There was a problem hiding this comment.
Pull request overview
Adds a new evaluation to the eval registry to measure Turkish proverb completion from partial prompts, backed by a small 20-sample JSONL dataset.
Changes:
- Added
turkish-proverbseval registry entry using theMatchevaluator and accuracy metric. - Added a 20-item Turkish proverb completion dataset under
evals/registry/data/turkish-proverbs/.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 4 comments.
| File | Description |
|---|---|
evals/registry/evals/turkish-proverbs.yaml |
Registers the new Turkish proverb completion eval and points it at the dataset. |
evals/registry/data/turkish-proverbs/samples.jsonl |
Provides 20 proverb-completion prompts and expected completions (some with diacriticless variants). |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
+6
to
+9
| turkish-proverbs.dev.v0: | ||
| class: evals.elsuite.basic.match:Match | ||
| args: | ||
| samples_jsonl: turkish-proverbs/samples.jsonl No newline at end of file |
Comment on lines
+4
to
+5
| {"input": "Aşağıdaki Türkçe atasözünü yalnızca eksik kısmıyla tamamlayın:\nGülü seven ____", "ideal": "dikenine katlanır"} | ||
| {"input": "Aşağıdaki Türkçe atasözünü yalnızca eksik kısmıyla tamamlayın:\nBugünün işini ____", "ideal": "yarına bırakma"} |
| {"input": "Aşağıdaki Türkçe atasözünü yalnızca eksik kısmıyla tamamlayın:\nDost kara günde ____", "ideal": "belli olur"} | ||
| {"input": "Aşağıdaki Türkçe atasözünü yalnızca eksik kısmıyla tamamlayın:\nAk akçe ____", "ideal": ["kara gün içindir", "kara gun icindir"]} | ||
| {"input": "Aşağıdaki Türkçe atasözünü yalnızca eksik kısmıyla tamamlayın:\nPerşembenin gelişi ____", "ideal": ["çarşambadan bellidir", "carsambadan bellidir"]} | ||
| {"input": "Aşağıdaki Türkçe atasözünü yalnızca eksik kısmıyla tamamlayın:\nEv alma, ____", "ideal": "komşu al"} |
| {"input": "Aşağıdaki Türkçe atasözünü yalnızca eksik kısmıyla tamamlayın:\nEv alma, ____", "ideal": "komşu al"} | ||
| {"input": "Aşağıdaki Türkçe atasözünü yalnızca eksik kısmıyla tamamlayın:\nHamama giren ____", "ideal": "terler"} | ||
| {"input": "Aşağıdaki Türkçe atasözünü yalnızca eksik kısmıyla tamamlayın:\nTaşıma suyla ____", "ideal": ["değirmen dönmez", "degirmen donmez"]} | ||
| {"input": "Aşağıdaki Türkçe atasözünü yalnızca eksik kısmıyla tamamlayın:\nLafla peynir gemisi ____", "ideal": "yürümez"} |
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
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.
Overview
Adds a new Turkish-language eval focused on proverb completion.
What this eval covers
This eval tests whether a model can correctly complete widely used Turkish proverbs from a partial prompt. The dataset includes 20 common, canonical proverb completions with short exact-match answers.
Examples include:
Eval type
This uses
evals.elsuite.basic.match:Matchwith exact-match grading.Files added
evals/registry/data/turkish-proverbs/samples.jsonlevals/registry/evals/turkish-proverbs.yaml