Grade Guard: A Smart System for Short Answer Automated Grading

Grade Guard is an LLM-based automated short answer grading system that introduces an Indecisiveness Score to reflect uncertainty in predicted grades and uses self-reflection to flag answers requiring human re-evaluation. The framework fine-tunes temperature parameters and introduces Confidence-Aware Loss to improve grading accuracy compared to traditional LLM approaches.

The advent of large language models (LLMs) in the education sector has provided impetus to automate grading short answer questions. LLMs make evaluating short answers very efficient, thus addressing issues like staff shortage. However, in the task of Automated Short Answer Grading (ASAG), LLM responses are influenced by diverse perspectives in their training dataset, leading to inaccuracies in evaluating nuanced or partially correct answers. To address this challenge, we propose a novel framewor

Study Type

Source

Framework Categories

Tool Types

Tags