Anat Yarden Group

Recognizing the ecological roles of microorganisms as drivers of marine biogeochemical cycles and how they are influenced by seawater pollution, warming, and acidification is essential to understanding climate change mechanisms and their global impacts. We call for updating current science teaching standards by linking microscale processes and macroscale dynamics in the context of marine ecosystems to promote ocean and climate literacy among the next generation.

The educational landscape is rapidly evolving, driven by Generative Artificial Intelligence (GenAI) advancements. As GenAI transforms educational practices, a key area of impact is developing automatic scoring systems to efficiently and accurately assess students' problem-solving and explanation skills. This study introduces a novel prompt engineering strategy, Reflective Prompt Engineering (RPE), which applies iterative human-AI collaboration through discussion and reflection with a powerful LLM to enhance scoring performance. In RPE, human experts guide the AI by integrating its inferred criteria and language into subsequent prompts, enabling reflective alignment and improvement. We applied RPE to score open-ended biology items using analytic grading rubrics, evaluating its performance against two benchmarks: a BERT-based scoring model and multiple examples prompts with no discussion. Performance (accuracy and Cohen's Kappa) was assessed in two scenarios: within-item and cross-items. RPE achieved excellent agreement with human experts (Cohen's Kappa > 0.8) using only 40-60 examples and consistently outperformed the multiple examples strategy, achieving significantly higher Kappa values. Our findings highlight the potential of RPE to optimise AI alignment with human-designed tasks and open pathways for broader applications across diverse domains, advancing automated evaluation practices with enhanced precision and adaptability.

Learning for complex world-making practices cannot be understood without embracing theoretical perspectives that acknowledge the complexity and dynamics of the interconnected and distributed among people and their environments nature of such practices. This symposium aims to advance the conceptual foundations for studying learning as an ecological phenomenon. It builds upon the recent special issue of Journal of the Learning Sciences, \u201cBeyonddisciplinary engagement: Researching the ecologies of interdisciplinary learning\u201d (Markauskaite et al., 2024). The papers in this special issue adopted diverse ecological perspectives to study interdisciplinary learning, offering unique insights into how personal resourcefulness, teamwork dynamics, institutional processes, and disciplinary cultures intertwine in this context. However, the underpinning conceptual issues of theorizing and empirically studying learningas an ecological phenomenon were not specifically examined. In this symposium, we extend this work to unpack different ecological conceptualizations of learning and discuss critical directions for further development