A LLM-Powered Automatic Grading Framework with Human-Level Guidelines Optimization

GradeOpt is a multi-agent LLM framework for automatic short-answer grading (ASAG) that uses self-reflection to optimize grading guidelines, evaluated on datasets measuring teachers' pedagogical knowledge and students' learning progress in mathematics and physical science.

Open-ended short-answer questions (SAGs) have been widely recognized as a powerful tool for providing deeper insights into learners' responses in the context of learning analytics (LA). However, SAGs often present challenges in practice due to the high grading workload and concerns about inconsistent assessments. With recent advancements in natural language processing (NLP), automatic short-answer grading (ASAG) offers a promising solution to these challenges. Despite this, current ASAG algorith

Study Type

Source

Framework Categories

Tool Types

Tags