feat(text-metrics): split oneig_alignment

[davidberenstein1957]

Summary

• Split oneig_alignment into its own stacked branch/PR
• Add OneIGAlignmentMetric implementation
• Add OneIG alignment subset benchmark entries and focused alignment tests

Test plan

• Run uv run pytest tests/evaluation/test_text_metrics.py -k oneig_alignment

Made with Cursor

[cursor]

Cursor Bugbot has reviewed your changes and found 3 potential issues.

^{❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.}

Comment @cursor review or bugbot run to trigger another review on this PR

^{Reviewed by Cursor Bugbot for commit 2627d78. Configure here.}

[cursor]

OneIG subset benchmarks fail to register at import

High Severity

The new OneIG benchmarks create lookup keys (e.g., OneIGAnimeStylization) that are missing from base_datasets. This causes BenchmarkRegistry._register to raise a ValueError, failing module import for pruna.evaluation.benchmarks and its dependents. The original OneIG entry was also removed.

 

^{Reviewed by Cursor Bugbot for commit 2627d78. Configure here.}

[cursor]

OneIG record test calls function with wrong signature

Medium Severity

The test_to_oneig_record_strips_null_questions_and_dependencies test calls _to_oneig_record with an incorrect number of arguments, causing a TypeError. The test also asserts that null-valued questions and dependencies are stripped, a behavior not implemented in _to_oneig_record.

 

^{Reviewed by Cursor Bugbot for commit 2627d78. Configure here.}

[cursor]

OneIG Multilingualism subset has no alignment questions

Medium Severity

The OneIG Multilingualism benchmark wires the oneig_alignment metric, but _CATEGORY_TO_QD in prompt.py only maps Anime_Stylization, Portrait, and General_Object to Q_D files. Multilingualism rows therefore receive an empty questions dict in _to_oneig_record, and OneIGAlignmentMetric.update raises ValueError whenever questions is empty. Running this benchmark would error out on every sample rather than produce alignment scores.

Additional Locations (1)

• src/pruna/evaluation/metrics/metric_oneig_alignment.py#L213-L218

 

^{Reviewed by Cursor Bugbot for commit 2627d78. Configure here.}