L2D-Clinical: Learning to Defer for Adaptive Model Selection in Clinical Text Classification

arXiv:2604.13285v1 Announce Type: cross Abstract: Clinical text classification requires choosing between specialized fine-tuned models (BERT variants) and general-purpose large language models (LLMs), yet neither dominates across all instances. We introduce Learning to Defer for clinical text (L2D-Clinical), a framework that learns when a BERT classifier should defer to an LLM based on uncertainty signals and text characteristics. Unlike prior L2D work that defers to human experts assumed univer