LAMBADA Cloze

The LAMBADA last-word task with an explicit cloze blank in the prompt, scored as log-likelihood accuracy on the withheld word.

Also known as: lambada openai cloze, lambada standard cloze

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
Subcategorycloze-format last-word prediction on LAMBADA passages
Page statusunknown
Metricaccuracy (log-likelihood exact match on the last word); perplexity also reported
Directionhigher_is_better
Unit%
Dataset size5153
Dataset licenceCC BY 4.0
PublisherUniversity of Trento (CIMeC); University of Amsterdam (dataset). EleutherAI (cloze harness configs)

What it measures

lambada_cloze is EleutherAI's cloze presentation of the LAMBADA dataset, not a new passage set. The model still sees a narrative passage whose final word is withheld, and must assign highest probability to that word. The cloze YAMLs differ from lambada_standard and lambada_openai only in the prompt: after the passage-without-last-word they insert a visible blank of the form " ____. ->" before scoring the last word. The original 2016 construction still applies: humans could guess the word from the full passage and could not from the last sentence alone.

Task format

Cloze / language modelling: passage with last word replaced by an explicit blank, scored as log-likelihood of the true last word rather than free generation or multiple choice.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub