Overview of AI Grading of Physics Olympiad Exams

TL;DR

This paper reviews existing AI grading techniques for physics Olympiad exams, proposes a multi-modal AI grading framework, and evaluates it considering ethical principles to improve automated assessment accuracy.

Contribution

It introduces a novel multi-modal AI grading framework specifically designed for diverse physics exam questions and assesses its alignment with ethical standards.

Findings

Systematic review of physics grading techniques

Proposed multi-modal AI grading framework

Framework evaluated against AI ethical principles

Abstract

Automatically grading the diverse range of question types in high school physics problem is a challenge that requires automated grading techniques from different fields. We report the findings of a Systematic Literature Review of potential physics grading techniques. We propose a multi-modal AI grading framework to address these challenges and examine our framework in light of Australia's AI Ethical Principles.