mlfoundations / mlfoundations/evalchemy
Only return loose result in IFEval?
Open
Nobody has claimed this yet.
- Dominant language
- HTML
- Stars
- 610
- Forks
- 87
- PR merge metrics
- No merged PRs in 30d
Description
According to the function "evaluate_accuracy" in eval.chat_benchmarks.IFEval.evaluation.py, the first strict result will be overwritten and never returned?
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Open eval.chat_benchmarks.IFEval.evaluation.py and inspect evaluate_accuracy, focusing on how the strict and loose results are assigned and returned. Confirm the intended result-selection behavior from the surrounding evaluation logic, then verify that the first strict result is preserved and returned instead of being overwritten.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 58/100