This work compares fine-tuning small language models with prompting large language models, highlighting quality improvements for generating structured outputs.
Large Language Models (LLMs) such as GPT-4o can handle a wide range of complex tasks with the right prompt. As per token costs are reduced, the advantages of fine-tuning Small Language Models (SLMs) for real-world applications -- faster inference, lower costs -- may no longer be clear. In this work, we present evidence that, for domain-specific tasks that require structured outputs, SLMs still have a quality advantage. We compare fine-tuning an SLM against prompting LLMs on the task of generating low-code workflows in JSON form. We observe that while a good prompt can yield reasonable results, fine-tuning improves quality by 10% on average. We also perform systematic error analysis to reveal model limitations.
No takes yet. Share an insight, caveat, or question.
Ayala et al. (2025) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: