Fine-tuning for Better Few Shot Prompting: An Empirical Comparison for Short Answer Grading
This work addresses automated short answer grading for educators and researchers, but it is incremental as it compares existing fine-tuning and prompting methods.
The study compared fine-tuning methods (including OpenAI's service and QLORA) with few-shot prompting for automated short answer grading, finding that fine-tuning outperformed few-shot baselines for closed models but had limited utility for open-weight models, with improvements seen using synthetic data for Llama 3.1 8B-Instruct.
Research to improve Automated Short Answer Grading has recently focused on Large Language Models (LLMs) with prompt engineering and no- or few-shot prompting to achieve best results. This is in contrast to the fine-tuning approach, which has historically required large-scale compute clusters inaccessible to most users. New closed-model approaches such as OpenAI's fine-tuning service promise results with as few as 100 examples, while methods using open weights such as quantized low-rank adaptive (QLORA) can be used to fine-tune models on consumer GPUs. We evaluate both of these fine-tuning methods, measuring their interaction with few-shot prompting for automated short answer grading (ASAG) with structured (JSON) outputs. Our results show that finetuning with small amounts of data has limited utility for Llama open-weight models, but that fine-tuning methods can outperform few-shot baseline instruction-tuned LLMs for OpenAI's closed models. While our evaluation set is limited, we find some evidence that the observed benefits of finetuning may be impacted by the domain subject matter. Lastly, we observed dramatic improvement with the LLama 3.1 8B-Instruct open-weight model by seeding the initial training examples with a significant amount of cheaply generated synthetic training data.