Subject-Verb Agreement

Programmatic BIG-bench task that scores whether a model assigns higher probability to the grammatically correct verb form across syntactic constructions with long-distance or nested agreement.

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
Subcategorysyntactic structure / linguistic probing
Page statusactive
Metricaccuracy (mean condition score, 'full')
Directionhigher_is_better
Dataset size32116
Dataset licenceApache-2.0
PublisherGoogle (BIG-bench collaboration), with data from four earlier academic papers

What it measures

This task probes whether a language model's internal representations capture the hierarchical (not just linear) structure of sentences, using subject-verb number agreement as the diagnostic. Given a sentence preamble such as 'The keys to the cabinet ...', the model must assign higher probability to the grammatically correct verb form (here, plural 'are') than to the form that would agree with a nearer but grammatically irrelevant noun ('cabinet', which would suggest singular 'is'). Constructions range from trivially adjacent subject-verb pairs to deeply nested relative clauses where multiple intervening nouns of conflicting grammatical number ('attractors') can mislead a model that relies on surface proximity rather than syntactic structure.

Task format

Two-way forced choice via log-probability comparison: for each item the model's conditional log-probability on the correct verb form is compared against the incorrect form, scored 1 if the correct form is more probable, 0 otherwise, averaged per condition and then across conditions/subtasks.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub