Search for: All records

Short answer assessment is a vital component of science education, allowing evaluation of students' complex three-dimensional understanding. Large language models (LLMs) that possess human-like ability in linguistic tasks are increasingly popular in assisting human graders to reduce their workload. However, LLMs' limitations in domain knowledge restrict their understanding in task-specific requirements and hinder their ability to achieve satisfactory performance. Retrieval-augmented generation (RAG) emerges as a promising solution by enabling LLMs to access relevant domain-specific knowledge during assessment. In this work, we propose an adaptive RAG framework for automated grading that dynamically retrieves and incorporates domain-specific knowledge based on the question and student answer context. Our approach combines semantic search and curated educational sources to retrieve valuable reference materials. Experimental results in a science education dataset demonstrate that our system achieves an improvement in grading accuracy compared to baseline LLM approaches. The findings suggest that RAG-enhanced grading systems can serve as reliable support with efficient performance gains. 

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. 

The 1988 Yellowstone fire altered the structure of the local forest ecosystem and left large non-recovery areas. This study assessed the pre-fire drivers and post-fire characteristics of the recovery and non-recovery areas and examined possible reasons driving non-recovery of the areas post-fire disturbance. Non-recovery and recovery areas were sampled with 44,629 points and 77,501 points, from which attribute values related to topography, climate, and subsequent soil conditions were extracted. We calculated the 1988 Yellowstone fire burn thresholds using the differenced Normalized Burn Ratio (dNBR) and official fire maps. We used a burn severity map from the US Forest Service to calculate the burn severity values. Spatial regressions and Chi-Square tests were applied to determine the statistically significant characteristics of a lack of recovery. The non-recovery areas were found to cover 1005.25 km2. Among 11 variables considered as potential factors driving recovery areas and 13 variables driving non-recovery areas, elevation and maximum temperature were found to have high Variance Inflation Factors (4.73 and 4.72). The results showed that non-recovery areas all experienced severe burns and were located at areas with steeper slopes (13.99°), more precipitation (871.73 mm), higher pre-fire vegetation density (NDVI = 0.38), higher bulk density (750.03 kg/m3), lower soil organic matter (165.61 g/kg), and lower total nitrogen (60.97 mg/L). Chi-square analyses revealed statistically different pre-fire forest species (p < 0.01) and soil order (p < 0.01) in the recovery and non-recovery areas. Although Inceptisols dominated in both recovery and non-recovery areas, however, the composition of Mollisols was higher in the non-recovery areas (14%) compared to the recovery areas (11%). This indicated the ecological memory of the non-recovery site reverting to grassland post-disturbance. Unlike conventional studies only focusing on recovery areas, this study analyzed the non-recovery areas and found the key characteristics that make a landscape not resilient to the 1988 Yellowstone fire. The significant effects of elevation, precipitation, and soil pH on recovery may be significant to the forest management and forest resilience in the post-fire period. 

High-resolution endoscopic optical imaging is a crucial technique in biological imaging to examine the inside organs. There is a trade-off between lateral resolution and depth of focus in such applications. Traditional Optical Coherence Tomography provides an increased depth range but falls short of desired resolution. The combination of both higher resolution and larger imaging depth of focus of metalens can improve the clinical utility of endoscopic optical imaging. In this work, we designed, analyzed, and fabricated a 500 µm diameter metalens operating at 1300 nm to achieve high resolution and large imaging depth of focus, therefore, addressing this need. The full width at half maximum and depth of focus for the proposed metalens are 3.10 and 286 µm, respectively. 

Global warming and related disturbances, such as drought, water, and heat stress, are causing forest decline resulting in regime shifts. Conventional studies have combined tree-ring width (TRW) and the normalized difference vegetation index (NDVI) to reconstruct NDVI values and ignored the influences of mixed land covers. We built an integrated TRW-NDVI model and reconstructed the annual NDVI maps by using 622 Landsat satellite images and tree cores from 15 plots using point-by-point regression. Our model performed well in the study area, as demonstrated by significant reconstructions for 71.14% (p < 0.05) of the area with the exclusion of water and barren areas. The error rate between the reconstructed NDVI using the conventional approach and our approach could reach 10.36%. The 30 m resolution reconstructed NDVI images in the recent 100 years clearly displayed a decrease in vegetation density and detected decades-long regime shifts from 1906 to 2015. Our study site experienced five regime shifts, markedly the 1930s and 1950s, which were megadroughts across North America. With fine resolution maps, regime shifts could be observed annually at the centennial scale. They can also be used to understand how the Yellowstone ecosystem has gradually changed with its ecological legacies in the last century.