The Alignment Illusion in Multimodal Large Language Models
Across 13 multimodal LLMs, standard visual-text alignment scores miss corrupted visuals, an effect called the alignment illusion.
The paper challenges the idea that layer-wise visual-text similarity in multimodal LLMs shows genuine content-level integration. Across 13 models from five families, from 0.5B to 72B parameters, replacing projector-output visual tokens with Gaussian noise sharply reduces task accuracy, yet CKA, SVCCA, MIR, and the leading principal-angle cosine often fail to separate the corrupted stream. The authors call this the alignment illusion and trace it to anisotropic MLP down-projections that pull tokens toward shared directions. Their principal-angle gap, the difference between the top two principal-angle cosines, tracks accuracy more consistently under graded visual corruption.
- Gaussian noise in visual tokens cuts accuracy but scalar scores often stay high.
- Tests cover 13 MLLMs from five families, spanning 0.5B to 72B parameters.
- Anisotropic MLP down-projections create mostly one-dimensional weight-induced alignment.
- The principal-angle gap tracks accuracy better than CKA, SVCCA, and MIR.
From the original article
1 min read at arxiv.orgLayer-wise visual-text similarity in Multimodal Large Language Models (MLLMs) is widely interpreted as evidence that the language model progressively integrates visual content into a shared representation space. This reading rests on the assumption that scalar alignment scores reflect content-level cross-modal interaction. To test this assumption, we apply controlled interventions to the visual stream.
By Hong-Han Wang · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.