Language priors can override vision in multimodal AI models
Seeing is Believing: Benchmarking and Mitigating the Interference of Language Priors on Visual Perception in MLLMs
Computer Vision and Pattern Recognition
Summary
Multimodal large language models sometimes trust their language guesses more than what they actually see, leading to wrong answers about images. The authors found that models don’t always share the same language biases, and some questions can be answered right without looking at the image, making simple accuracy measures misleading. They created a new test called ViSiP-Bench with tricky examples to better measure how much models rely on language guesses versus visual evidence. They also made a method, MAPS, that fine-tunes models to reduce overreliance on these language guesses without breaking their general skills.
What this means in practice
- •For multimodal ai developers: Test models for bias toward language-based guesses over visual info using ViSiP-Bench to improve image understanding accuracy.
- •For ai model trainers: Use MAPS fine-tuning to reduce excessive language bias in multimodal models, improving their reliance on actual image input.
Authors
Li Ma, Yan Zhuang, Jiawen Deng, Fuji Ren
Abstract
Language priors in MLLMs can override visual evidence, impairing visual perception. Existing benchmarks assume shared priors across models and rely solely on accuracy. However, cross-model prior agreement falls below 80%, and over 15% of items can be answered correctly without any image, causing accuracy to overestimate prior resistance. To address these limitations, we introduce ViSiP-Bench, a benchmark grounded in rare-but-real scenarios across six prior categories, with a model-aware dynamic prior induction protocol and three metrics that more precisely and continuously measure prior resistance than accuracy alone. Evaluating 24 models reveals that prior adherence is pervasive, does not improve with scale, and larger models tend to either strongly override their priors or firmly adhere to them. We therefore propose MAPS, which identifies each model's strongest priors and fine-tunes on factually grounded knowledge to soften excessive prior reliance without disrupting general capabilities.