Summary of “i Understand Why I Got This Grade”: Automatic Short Answer Grading with Feedback, by Dishank Aggarwal et al.

“I understand why I got this grade”: Automatic Short Answer Grading with Feedback

by Dishank Aggarwal, Pushpak Bhattacharyya, Bhaskaran Raman

First submitted to arxiv on: 30 Jun 2024

GrooveSquid.com Paper Summaries

GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!

Summary difficulty	Written by	Summary
High	Paper authors	High Difficulty Summary Read the original abstract here
Medium	GrooveSquid.com (original content)	Medium Difficulty Summary The paper introduces Engineering Short Answer Feedback (EngSAF), a dataset of 5.8k student answers with reference answers and questions, designed to improve automated grading in education. The EngSAF dataset covers various subjects, questions, and answer patterns from multiple engineering domains. State-of-the-art large language models’ generative capabilities are leveraged with the Label-Aware Synthetic Feedback Generation (LASFG) strategy to include feedback in the dataset. This paper emphasizes the importance of enhanced feedback in practical educational settings, outlines dataset annotation and feedback generation processes, conducts an EngSAF analysis, and provides different LLMs-based zero-shot and finetuned baselines for future comparison. The ASAG system’s efficiency and effectiveness are demonstrated through its deployment in a real-world end-semester exam at the Indian Institute of Technology Bombay (IITB), showcasing its practical viability and potential for broader implementation in educational institutions.
Low	GrooveSquid.com (original content)	Low Difficulty Summary The paper is about making it easier to give feedback on student answers online. This is important because feedback helps students learn, and currently, grading can be a time-consuming task for teachers. The researchers created a big dataset of student answers with the correct answers and questions to help machines grade papers better. They used special computer models to generate this data and made sure it covers many different subjects and types of answers. The paper shows how this system works and why it’s important, and it even tests it on real exams at an Indian university to see if it can be used in the future.