Understanding Fables

189 paraphrased fables paired with five candidate morals test narrative understanding and cross-domain generalization.

Also known as: BIG-bench Understanding Fables

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categoryreasoning
Subcategorynarrative moral selection
Page statusactive
Metricmultiple_choice_grade accuracy
Directionhigher_is_better
Unit%
Dataset size189
PublisherBIG-bench collaboration

What it measures

The model reads a short fable and selects the moral that best expresses its lesson. Fables are paraphrased from Aesop-related sources with plausible distractor morals.

Task format

Five-choice multiple choice with one correct moral and four distractors.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub