Story Cloze Test

Story Cloze Test asks a model to pick the correct one of two endings to a four-sentence story; the original 2016 set has documented annotation biases exploitable without real story understanding.

Also known as: StoryCloze, ROCStories Cloze Test

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
Subcategorycommonsense story-ending selection (binary forced-choice cloze test)
Page statussaturated
MetricAccuracy (2-way forced choice)
Directionhigher_is_better
Unit%
Dataset size3742
Dataset licenceNot established from any source read for this page (Hugging Face tags it 'unknown'); the official Rochester site distributes the data free of charge after a mandatory access-request form
PublisherUniversity of Rochester

What it measures

Story Cloze Test gives a model a four-sentence everyday story and two possible one-sentence endings, and asks it to pick the ending that actually fits -- a "commonsense reasoning framework for evaluating story understanding, story generation, and script learning," in the original authors' own words, designed to replace the earlier "Narrative Cloze Test" as a way to measure whether a system has learned the causal and temporal structure of ordinary events. The test set is a small, separately-curated slice of a much larger corpus the same paper introduced, ROCStories: roughly 50,000 five-sentence commonsense stories written by crowdworkers, intended for training and for story-generation research, from which the smaller cloze-test instances (four-sentence context plus right/wrong endings) were built as a held-out evaluation set. A model that has learned genuine narrative and commonsense structure should prefer the coherent ending; the task is designed to be easy for a human reader and hard for a system relying only on shallow textual cues.

Task format

Two-way forced choice: given a four-sentence story and two candidate fifth sentences, select the one that is the coherent, correct ending. Most harnesses implement this as loglikelihood comparison (which candidate ending is more probable given the context) rather than free generation.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub