Equation 3 · The Benchmarks That Don't Need the Image
What does this equation mean?
Read the formula alongside the article passage below. Each part has a deeper page with its role in the equation, the supporting passage and nearby citations.
the accuracy of that same model’s underlying text-only language backbone. Read the equation part by part below; each part has a contextual explanation and a link to its mathematical background.
Read it piece by piece
Symbol S_t
the accuracy of that same model’s underlying text-only language backbone.
subscript
The lower label selects a particular version, component, or indexed member of the quantity. For example, x₀ and xₜ can be values at different positions.
How to interpret it
Read this expression with the definitions, units, and assumptions supplied by the article.
What the article says around this equation
The first is measurement-time ablation : take an already-trained system, rerun the exact same benchmark items with one channel removed at inference, and compare. This is what the original VQA paper did with its question-only baseline [ 1 ] , and it is what a 2024 audit of vision-language benchmarks did formally, by defining two paired metrics from three separately measured accuracies. Let be a model’s accuracy on a benchmark with the image present, its accuracy on the same items with the image withheld, and the accuracy of that same model’s underlying text-only language backbone, evaluated on its own before any multimodal training touched it. The audit’s two metrics are then
Sources cited in the surrounding passage
These citations give research context. Read each source to check which claims it supports.