Litcius/Paper detail

Small or Large? Zero-Shot or Finetuned? Guiding Language Model Choice for Specialized Applications in Healthcare

Lovedeep Gondara, Jonathan Simkin, Graham Sayle, Shebnum Devji, Gregory Arbour, Raymond T. Ng

2025Machine Learning and Knowledge Extraction6 citationsDOIOpen Access PDF

Abstract

Objectives: To guide language model (LM) selection by comparing finetuning vs. zero-shot use, generic pretraining vs. domain-adjacent vs. further domain-specific pretraining, and bidirectional language models (BiLMs) such as BERT vs. unidirectional LMs (LLMs) for clinical classification. Materials and Methods: We evaluated BiLMs (RoBERTa, PathologyBERT, Gatortron) and LLM (Mistral nemo instruct 12B) on three British Columbia Cancer Registry (BCCR) pathology classification tasks varying in difficulty/data size. We assessed zero-shot vs. finetuned BiLMs, zero-shot LLM, and further BCCR-specific pretraining using macro-average F1 scores. Results: Finetuned BiLMs outperformed zero-shot BiLMs and zero-shot LLM. The zero-shot LLM outperformed zero-shot BiLMs but was consistently outperformed by finetuned BiLMs. Domain-adjacent BiLMs generally outperformed generic BiLMs after finetuning. Further domain-specific pretraining boosted complex/low-data task performance, with otherwise modest gains. Conclusions: For specialized classification, finetuning BiLMs is crucial, often surpassing zero-shot LLMs. Domain-adjacent pretrained models are recommended. Further domain-specific pretraining provides significant performance boosts, especially for complex/low-data scenarios. BiLMs remain relevant, offering strong performance/resource balance for targeted clinical tasks.

Topics & Concepts

Computer scienceTask (project management)Language modelSelection (genetic algorithm)Artificial intelligenceNatural language processingExploitHuman–computer interactionHealth careMachine learningLanguage understandingTask analysisVariety (cybernetics)ArchitectureConstructed languageClinical PracticeHealthcare systemData scienceSemantics (computer science)Topic ModelingBiomedical Text Mining and OntologiesData Quality and Management
Small or Large? Zero-Shot or Finetuned? Guiding Language Model Choice for Specialized Applications in Healthcare | Litcius