To what extent does modality imbalance affect the accuracy and routing stability of multimodal language models

Abstract

Abstract: The rise of Multimodal Large Language Models (MLLMs) has significantly advanced the capabilities of AI systems to understand and generate content across diverse modalities such as text, images, audio, video, and sensory data. By leveraging the reasoning prowess of Large Language Models (LLMs), MLLMs unify multiple input formats into a coherent framework, enabling unprecedented performance in multimodal tasks. This survey provides a comprehensive overview of the architectural innovations, training paradigms, data resources, and evaluation benchmarks that have shaped the evolution of MLLMs. We r

Research Question

To what extent does modality imbalance affect the accuracy and routing stability of multimodal language models as measured by performance on MMBench and SEED-Bench evaluation suites?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Truth-Engine Gate Verdict

This record has not completed Gate 2 of the verification pipeline (a type-checked Lean4 proof for mathematical claims, or a sealed-sandbox reproduction for empirical claims). It is a literature synthesis only. VERIFIED requires an attached reproducible artifact (Lean4 proof source, or repro script and results) before this status can be set; it is not derived from review score or claim count.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance