Human Multimodal Language Understanding (MLU) aims to infer human intentions by integrating related cues from heterogeneous modalities. Existing works predominantly follow a ``learning to attend" paradigm, which maximizes mutual information between data and labels to enhance predictive performance. However, such methods are vulnerable to unintended dataset biases, causing models to conflate statistical shortcuts with genuine causal features and resulting in degraded out-of-distribution (OOD) generalization. To alleviate this issue, we introduce a Causal Multimodal Information Bottleneck (CaMIB) model that leverages causal principles rather than traditional likelihood. Concretely, we first applies the information bottleneck to filter unimodal inputs, removing task-irrelevant noise. A parameterized mask generator then disentangles the fused multimodal representation into causal and shortcut subrepresentations. To ensure global consistency of causal features, we incorporate an instrumental variable constraint, and further adopt backdoor adjustment by randomly recombining causal and shortcut features to stabilize causal estimation. Extensive experiments on multimodal sentiment analysis, humor detection, and sarcasm detection, along with OOD test sets, demonstrate the effectiveness of CaMIB. Theoretical and empirical analyses further highlight its interpretability and soundness.