Beyond Scores: A Modular RAG-Based System for Automatic Short Answer Scoring with Feedback
This work provides a scalable and cost-effective solution for educators to reduce grading burden and provide explainable feedback, particularly for new or unseen questions.
This paper addresses the challenge of automatic short answer scoring with feedback (ASAS-F) by proposing a modular retrieval-augmented generation (RAG) system. The system scores answers and generates feedback in zero-shot and few-shot settings, achieving a 9% improvement in scoring accuracy on unseen questions compared to fine-tuning methods.
Automatic short answer scoring (ASAS) helps reduce the grading burden on educators but often lacks detailed, explainable feedback. Existing methods in ASAS with feedback (ASAS-F) rely on fine-tuning language models with limited datasets, which is resource-intensive and struggles to generalize across contexts. Recent approaches using large language models (LLMs) have focused on scoring without extensive fine-tuning. However, they often rely heavily on prompt engineering and either fail to generate elaborated feedback or do not adequately evaluate it. In this paper, we propose a modular retrieval augmented generation based ASAS-F system that scores answers and generates feedback in strict zero-shot and few-shot learning scenarios. We design our system to be adaptable to various educational tasks without extensive prompt engineering using an automatic prompt generation framework. Results show an improvement in scoring accuracy by 9\% on unseen questions compared to fine-tuning, offering a scalable and cost-effective solution.