Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
The paper introduces L2D-Clinical, a learning-to-defer framework that adaptively selects between specialized BERT models and general-purpose LLMs for clinical text classification based on uncertainty signals and text characteristics. Unlike prior work, L2D-Clinical defers to another model rather than a human expert, enabling performance gains when the LLM complements BERT. Experiments on ADE detection and treatment outcome classification show that L2D-Clinical improves F1 scores by selectively deferring to the LLM on a small percentage of instances where the LLM's strengths compensate for BERT's weaknesses.
Stop blindly trusting your fine-tuned BERT model: selectively deferring to an LLM on just 7-17% of clinical text classification instances can boost F1 scores by up to 9.3 points.
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 universally superior, our approach enables adaptive deferral-improving accuracy when the LLM complements BERT. We evaluate on two English clinical tasks: (1) ADE detection (ADE Corpus V2), where BioBERT (F1=0.911) outperforms the LLM (F1=0.765), and (2) treatment outcome classification (MIMIC-IV with multi-LLM consensus ground truth), where GPT-5-nano (F1=0.967) outperforms ClinicalBERT (F1=0.887). On ADE, L2D-Clinical achieves F1=0.928 (+1.7 points over BERT) by selectively deferring 7% of instances where the LLM's high recall compensates for BERT's misses. On MIMIC, L2D-Clinical achieves F1=0.980 (+9.3 points over BERT) by deferring only 16.8\% of cases to the LLM. The key insight is that L2D-Clinical learns to selectively leverage LLM strengths while minimizing API costs.