Yingnan Deng

Submitted: 07 February 2026 You are already at the latest version This paper addresses the problem of text classification models being vulnerable and lacking robustness under adversarial perturbations by proposing a robust text classification method based on large language model calibration. The method builds on a pretrained language model and constructs a multi-stage framework for semantic representation and confidence regulation.

Submitted: 11 December 2025 You are already at the latest version This study addresses the challenges of semantic mixing, limited interpretability, and complex feature structures in fine-grained sentiment and opinion classification by proposing an interpretable feature disentanglement framework built on the latent space of large language models.