Related papers: Exploring the Structure of Misconceptions in the F…
Analysis of institutional data for physics majors showing predictive relationships between required mathematics and physics courses in various years is important for contemplating how the courses build on each other and whether there is…
We suggest one redefinition of common clusters of questions used to analyze student responses on the Force and Motion Conceptual Evaluation (FMCE). Our goal is to move beyond the expert/novice analysis of student learning based on…
Item Response Theory (IRT) is a popular assessment method used in education measurement, which builds on an assumption of a probability framework connecting students' innate ability and their actual performances on test items. The model…
Context: Students often misunderstand programming problem descriptions. This can lead them to solve the wrong problem, which creates frustration, obstructs learning, and imperils grades. Researchers have found that students can be made to…
The working memory capacity (WMC) of 400 Russian college students was measured using the Tarnow Unchunkable Test [2] which tests WMC alone without requiring explicit working memory operations. We found small-sized WMC differences by gender…
The Force Concept Inventory (FCI) can be used as an assessment tool to measure conceptual gains in a cohort of students. The FCI uses a conceptions/"misconceptions" lens rather than a context dependent perspective, such as…
Modeling plausible student misconceptions is critical for AI in education. In this work, we examine how large language models (LLMs) reason about misconceptions when generating multiple-choice distractors, a task that requires modeling…
Studies indicate that pre-existing misconceptions negatively impact the effectiveness of traditional physics education. Research has also shown that activity based instruction improves posttest scores on conceptual evaluations. However, the…
Recently, a method [7] was proposed to generate contrastive explanations for differentiable models such as deep neural networks, where one has complete access to the model. In this work, we propose a method, Model Agnostic Contrastive…
For Large Language Models (LLMs) to be reliably deployed, models must effectively know when not to answer: abstain. Reasoning models, in particular, have gained attention for impressive performance on complex tasks. However, reasoning…
Current deep learning models are not designed to simultaneously address three fundamental questions: predict class labels to solve a given classification task (the "What?"), simulate changes in the situation to evaluate how this impacts…
Recent studies propose membership inference (MI) attacks on deep models, where the goal is to infer if a sample has been used in the training process. Despite their apparent success, these studies only report accuracy, precision, and recall…
The widespread adoption of automatic sentiment and emotion classifiers makes it important to ensure that these tools perform reliably across different populations. Yet their reliability is typically assessed using benchmarks that rely on…
Studies examining gender differences in introductory physics show a consensus when it comes to a gender gap on conceptual assessments; however, the story is not as clear when it comes to differences in gendered performance on exams. This…
A partially unusual behaviour was found among 14 sophomore students of civil engineering who took a pre test for a free fall laboratory session, in the context of a general mechanics course. An analysis contemplating mathematics models and…
Physics curricula across the US fail to prepare students adequately to solve problems, especially novel problems. A new curriculum, Matter and Interactions (M&I), was designed to improve student learning by organizing concepts around…
Men and women systematically differ in their beliefs about their performance relative to others; in particular, men tend to be more overconfident. This paper provides support for one explanation for gender differences in overconfidence,…
The InfoNCE objective, originally introduced for contrastive representation learning, has become a popular choice for mutual information (MI) estimation, despite its indirect connection to MI. In this paper, we demonstrate why InfoNCE…
Detecting student misconceptions in open-ended responses is a longstanding challenge, demanding semantic precision and logical reasoning. We propose MiRAGE - Misconception Detection with Retrieval-Guided Multi-Stage Reasoning and Ensemble…
Combining the preferences of many rankers into one single consensus ranking is critical for consequential applications from hiring and admissions to lending. While group fairness has been extensively studied for classification, group…