Analysing Lightweight Large Language Models for Biomedical Named Entity Recognition on Diverse Ouput Formats
For healthcare settings with privacy and budget constraints, this work shows that lightweight LLMs can be effective alternatives to larger models for biomedical information extraction.
The paper investigates lightweight LLMs for biomedical NER, finding they achieve competitive performance to larger models while being more resource-efficient. Instruction tuning over many formats does not improve performance, but certain formats consistently yield better results.
Despite their strong linguistic capabilities, Large Language Models (LLMs) are computationally demanding and require substantial resources for fine-tuning, which is unadapted to privacy and budget constraints of many healthcare settings. To address this, we present an experimental analysis focused on Biomedical Named Entity Recognition using lightweight LLMs, we evaluate the impact of different output formats on model performance. The results reveal that lightweight LLMs can achieve competitive performance compared to the larger models, highlighting their potential as lightweight yet effective alternatives for biomedical information extraction. Our analysis shows that instruction tuning over many distinct formats does not improve performance, but identifies several format consistently associated with better performance.