Search for: All records

Open-text responses provide researchers and educators with rich, nuanced insights that multiple-choice questions cannot capture. When reliably assessed, such responses have the potential to enhance teaching and learning. However, scaling and consistently capturing these nuances remain significant challenges, limiting the widespread use of open-text questions in educational research and assessments. In this paper, we introduce and evaluate GradeOpt, a unified multiagent automatic short-answer grading (ASAG) framework that leverages large language models (LLMs) as graders for short-answer responses. More importantly, GradeOpt incorporates two additional LLM-based agents—the reflector and the refiner—into the multi-agent system. This enables GradeOpt to automatically optimize the original grading guidelines by performing self-reflection on its errors. To assess GradeOpt's effectiveness, we conducted experiments on two representative ASAG datasets, which include items designed to capture key aspects of teachers' pedagogical knowledge and students' learning progress. Our results demonstrate that GradeOpt consistently outperforms representative baselines in both grading accuracy and alignment with human evaluators across different knowledge domains. Finally, comprehensive ablation studies validate the contributions of GradeOpt's individual components, confirming their impact on overall performance. 

Abstract We face complex global issues such as climate change that challenge our ability as humans to manage them. Models have been used as a pivotal science and engineering tool to investigate, represent, explain, and predict phenomena or solve problems that involve multi-faceted systems across many fields. To fully explain complex phenomena or solve problems using models requires both systems thinking (ST) and computational thinking (CT). This study proposes a theoretical framework that uses modeling as a way to integrate ST and CT. We developed a framework to guide the complex process of developing curriculum, learning tools, support strategies, and assessments for engaging learners in ST and CT in the context of modeling. The framework includes essential aspects of ST and CT based on selected literature, and illustrates how each modeling practice draws upon aspects of both ST and CT to support explaining phenomena and solving problems. We use computational models to show how these ST and CT aspects are manifested in modeling. 

Abstract This paper introduces project-based learning (PBL) features for developing technological, curricular, and pedagogical supports to engage students in computational thinking (CT) through modeling. CT is recognized as the collection of approaches that  involve people in computational problem solving. CT supports students in deconstructing and reformulating a phenomenon such that it can be resolved using an information-processing agent (human or machine) to reach a scientifically appropriate explanation of a phenomenon. PBL allows students to learn by doing, to apply ideas, figure out how phenomena occur and solve challenging, compelling and complex problems. In doing so, students  take part in authentic science practices similar to those of professionals in science or engineering, such as computational thinking. This paper includes 1) CT and its associated aspects, 2) The foundation of PBL, 3) PBL design features to support CT through modeling, and 4) a curriculum example and associated student models to illustrate how particular design features can be used for developing high school physical science materials, such as an evaporative cooling unit to promote the teaching and learning of CT.