Fig. 3: Stages of prompt engineering LLMs as judges.
From: Current and future state of evaluation of large language models for medical summarization tasks
The three different aspects of prompt engineering expanded upon in section 5. The three sections - Zero-Shot and In-Context Learning (ICL), Parameter Efficient Fine Tuning (PEFT), and PEFT with Human Aware Loss Function (HALO) - fit together into a larger schema for training and prompting an LLM to serve as an evaluator to complement human expert evaluators.
