← All parts of this equation

Equation 7 · Part 1 · Building a Multimodal AI Application That Actually Uses Its Inputs

Symbol Delta_m

Δm=Accfull−Accablate(m).\Delta_m = \mathrm{Acc}_{\mathrm{full}} - \mathrm{Acc}_{\mathrm{ablate}(m)}.
Δm\Delta_m

What this part means

the small.

Its job in the formula

Deltama_m is part of the quantity the equation computes from the expression on the right.

Where the article explains it

A small Δm\Delta_m for a modality the task specification says should matter is the signature of a unimodal shortcut: the model is scoring well on the full-input evaluation without actually depending on that channel.

The passage around this formula

…For a task with a full-input accuracy Accfull\mathrm{Acc}_{\mathrm{full}} and an accuracy Accablate(m)\mathrm{Acc}_{\mathrm{ablate}(m)} measured with modality m removed, blanked, or replaced with noise, define Δm=Accfull−Accablate(m)\Delta_m = \mathrm{Acc}_{\mathrm{full}} - \mathrm{Acc}_{\mathrm{ablate}(m)}. A small Δm\Delta_m for a modality the task specification says should matter is the signature of a unimodal shortcut: the model is scoring well on the full-input evaluation without actually depending on that channel. This is not a hypothetical failure mode. Agrawal and colleagues showed that VQA models…

Read this part in the article →

Learn the underlying idea

A subscript is a label attached below a symbol. It often selects a time step, component, category, or member of a sequence.

Open the illustrated subscripts: which member of a family? guide →

See this notation across published equations →

Sources cited in the surrounding passage

These citations provide research context; check each source for the exact claim it supports.