Zero-shot classifier expansion aims to adapt existing model to new, unseen classes. It utilizes semantic descriptions of class attributes to learn a mapping from the semantic space to the classifier's weight space, without requiring new visual training data. However, the learning process for this mapping relies solely on the semantic-weight co-occurrence relationships observed on classes and lacks explicit modeling of inter-class differences, making it difficult for the model to capture the fundamental discriminative features required to define classification boundaries. To overcome this limitation, we reframe the problem from a causal perspective and introduce a novel framework driven by counterfactuals. Our method first generates factual descriptions alongside corresponding inter-class counterfactuals to pinpoint the causal attributes essential for classification, then refines these representations via a mutual purification process, and finally leverages a novel separation loss to explicitly push the factual and counterfactual classifier weights apart. This strategy compels the model to forge clearer and more discriminative classification boundaries. Extensive experiments on benchmark datasets demonstrate that our approach significantly outperforms existing state-of-the-art methods.