Sufficient Information

Tiny BIG-bench task of 39 short word problems that checks whether a model answers when given enough information and says 'I do not know' when it is not.

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
Subcategoryabstention / answerability judgment
Page statusactive
Metricexact string match
Directionhigher_is_better
Unit%
Dataset size39
Dataset licenceApache-2.0
PublisherGoogle (BIG-bench collaboration)

What it measures

Sufficient Information gives a model a short word problem and asks it to answer only if the prompt actually contains enough information to determine a correct answer, and to respond 'I do not know' otherwise. For example, 'Jamal is five years old. How old is Jamal?' has a determinate answer ('Five'), while 'Keisha has more phones than Kelsey. Kelsey has two phones. How many phones does Keisha have?' does not, since 'more' is not quantified. The task probes whether a model can recognize the limits of what it has been told, rather than defaulting to always producing a best-effort guess.

Task format

Free-text, zero-shot generation: the model is given a task prefix instructing it to answer from context or say 'I do not know', then a short word-problem prompt, and must produce the exact expected answer string or the fixed abstention string.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub