STaR-DRO: Stateful Tsallis Reweighting for Group-Robust Structured Prediction

arXiv:2604.09737v1 Announce Type: cross Abstract: Structured prediction requires models to generate ontology-constrained labels, grounded evidence, and valid structure under ambiguity, label skew, and heterogeneous group difficulty. We present a two-part framework for controllable inference and robust fine-tuning. First, we introduce a task-agnostic prompting strategy that combines XML-based instruction structure, disambiguation rules, verification-style reasoning, schema constraints, and self-v