Small but Significant: On the Promise of Small Language Models for Accessible AIED

GPT has become nearly synonymous with large language models (LLMs), an increasingly popular term in AIED proceedings. A simple keyword-based search reveals that 61% of the 76 long and short papers presented at AIED 2024 describe novel solutions using LLMs to address some of the long-standing challenges in education, and 43% specifically mention GPT. Although LLMs pioneered by GPT create exciting opportunities to strengthen the impact of AI on education, we argue that the field's predominant focus on GPT and other resource-intensive LLMs (with more than 10B parameters) risks neglecting the potential impact that small language models (SLMs) can make in providing resource-constrained institutions with equitable and affordable access to high-quality AI tools. Supported by positive results on knowledge component (KC) discovery, a critical challenge in AIED, we demonstrate that SLMs such as Phi-2 can produce an effective solution without elaborate prompting strategies. Hence, we call for more attention to developing SLM-based AIED approaches.

KCluster: An LLM-based Clustering Approach to Knowledge Component Discovery

Educators evaluate student knowledge using knowledge component (KC) models that map assessment questions to KCs. Still, designing KC models for large question banks remains an insurmountable challenge for instructors who need to analyze each question by hand. The growing use of Generative AI in education is expected only to aggravate this chronic deficiency of expert-designed KC models, as course engineers designing KCs struggle to keep up with the pace at which questions are generated. In this work, we propose KCluster, a novel KC discovery algorithm based on identifying clusters of congruent questions according to a new similarity metric induced by a large language model (LLM). We demonstrate in three datasets that an LLM can create an effective metric of question similarity, which a clustering algorithm can use to create KC models from questions with minimal human effort. Combining the strengths of LLM and clustering, KCluster generates descriptive KC labels and discovers KC models that predict student performance better than the best expert-designed models available. In anticipation of future work, we illustrate how KCluster can reveal insights into difficult KCs and suggest improvements to instruction.

Study of MRI-compatible Notched Plastic Ultrasonic Stator with FEM Simulation and Holography Validation

Intra-operative image guidance using magnetic resonance imaging (MRI) can significantly enhance the precision of surgical procedures, such as deep brain tumor ablation. However, the powerful magnetic fields and limited space within an MRI scanner require the use of robotic devices to aid surgeons. Piezoelectric motors are commonly utilized to drive these robots, with piezoelectric ultrasonic motors being particularly notable. These motors consist of a piezoelectric ring stator that is bonded to a rotor through frictional coupling. When the stator is excited at specific frequencies, it generates distinctive mode shapes with surface waves that exhibit both in-plane and out-of-plane displacement, leading to the rotation of the rotor. In this study, we continue our previous work and refine the motor design and performance, we combine finite element modeling (FEM) with stroboscopic and time-averaged digital holography to validate a further plastic-based ultrasonic motor with better rotary performance.

Influence of Event Duration on Automatic Wheeze Classification

Patients with respiratory conditions typically exhibit adventitious respiratory sounds, such as wheezes. Wheeze events have variable duration. In this work we studied the influence of event duration on wheeze classification, namely how the creation of the non-wheeze class affected the classifiers' performance. First, we evaluated several classifiers on an open access respiratory sound database, with the best one reaching sensitivity and specificity values of 98% and 95%, respectively. Then, by changing one parameter in the design of the non-wheeze class, i.e., event duration, the best classifier only reached sensitivity and specificity values of 55% and 76%, respectively. These results demonstrate the importance of experimental design on the assessment of wheeze classification algorithms' performance.