Verifiability Judgment

A HELM scenario that gives a model a generated statement and its cited source and asks it to judge whether the source fully, partially, or does not support the statement.

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.
Categoryknowledge
Subcategorycitation verification (statement-to-source support classification)
Page statusactive
MetricExact match / quasi-exact match against the human-annotated 3-way label
Directionhigher_is_better
Unitaccuracy
Dataset size11037
Dataset licenceMIT
PublisherStanford NLP Group (source dataset); Stanford CRFM (HELM implementation)

What it measures

Verifiability Judgment presents a statement, taken from a real generative search engine's response, together with the source document it cited, and asks the model to classify the citation relationship as "fully supports", "partially supports", or "does not support" the statement. It tests whether a model can perform the citation-verification step that underlies retrieval-augmented and search-grounded systems: reading a passage and judging whether it actually substantiates a specific claim, rather than merely appearing topically related.

Task format

Zero-shot (or few-shot, per HELM's default adapter configuration) text generation: HELM prompts the model with the statement and source under instructions to judge support as "fully supports", "partially supports" or "does not support", generating up to 10 tokens, and scores the output against the human-annotated label with exact match and quasi-exact match.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub