HypeLoRA: Hyper-Network-Generated LoRA Adapters for Calibrated Language Model Fine-Tuning

ArXi:2603.19278v1 Announce Type: cross Modern Transformer-based models frequently suffer from miscalibration, producing overconfident predictions that do not reflect true empirical frequencies. This work investigates the calibration dynamics of LoRA: Low-Rank Adaptation and a novel hyper-network-based adaptation framework as parameter-efficient alternatives to full fine-tuning for RoBERTa.