Short answer grading with sentence similarity and a few given grades
Year: 2025
Type: conference-paper
Abstract: We propose a novel method for automated short answer grading (ASAG) designed for practical use in real-world settings. The method combines LLM embedding similarity with a nonlinear regression function, enabling accurate prediction from a small number of expert-graded responses. In this use case, a grader manually assesses a few responses, while the remainder are scored automatically---a common scenario when graders need to review some responses to feel confident assigning final grades. The proposed method achieves an RMSE of 0.717 outperforming the fine-tuned state-of-the-art transformer models in grading accuracy, which are more labor-intensive and computationally demanding, limiting their practicality for many applications. This method stands out for its ease of implementation and effectiveness, offering reliable accuracy with minimal effort. The code is made public.
Authors: Michel Desmarais, Arman Bakhtiari, Ovide Kuichua, Samira Chiny Folefack Temfack, Chahe Nerguizian
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: green
OpenAlex ID: W6893497271
FWCI:
Cites:
Cited by:
Related to: