Advances in AI-Driven Educational Assessment

The field of educational assessment is undergoing significant transformations with the integration of large language models (LLMs). Recent developments indicate a shift towards more nuanced and multifaceted evaluation methods, moving beyond traditional holistic assessment approaches. This trend is characterized by the incorporation of pedagogical theories and frameworks, such as Vygotsky's theory and Bloom's Taxonomy, to inform the design of LLM-based assessment tools. These innovations aim to provide more accurate and comprehensive evaluations of student performance, addressing the complexities of cognitive development, disciplinary thinking, and academic competencies. Noteworthy papers in this area include PEMUTA, which pioneers a pedagogically-enriched framework for multi-granular undergraduate thesis assessment, and SketchMind, which introduces a cognitively grounded, multi-agent framework for evaluating student-drawn scientific sketches. Additionally, ELMES provides an automated framework for assessing LLMs in educational settings, while CoGrader and DUET demonstrate the potential of human-LLM collaborative grading systems and LLM-based tools for providing structured feedback on student-generated diagrams.

Sources

PEMUTA: Pedagogically-Enriched Multi-Granular Undergraduate Thesis Assessment

CIgrate: Automating CI Service Migration with Large Language Models

CoGrader: Transforming Instructors' Assessment of Project Reports through Collaborative LLM Integration

Opportunities and Challenges of LLMs in Education: An NLP Perspective

SketchMind: A Multi-Agent Cognitive Framework for Assessing Student-Drawn Scientific Sketches

ELMES: An Automated Framework for Evaluating Large Language Models in Educational Scenarios

Automated Feedback on Student-Generated UML and ER Diagrams Using Large Language Models

Built with on top of