Related papers: Evaluating Micro Parsons Problems as Exam Question…

This paper describes a new approach for learning from homework, called Peer-Assisted Reflection (PAR). PAR involves students using peer feedback to improve their work on open-ended homework problems. Collaborating with peers and revising…

Transformer architectures have achieved remarkable success across language, vision, and multimodal tasks, and there is growing demand for them to address in-context compositional learning tasks. In these tasks, models solve the target…

Code language models have emerged as useful tools for various programming tasks, yet they often struggle when it comes to complex ones. In this paper, we explore the potential of curriculum learning in enhancing the performance of these…

We examine the effect of misconceptions about friction on students' ability to solve problems and transfer from one context to another. We analyze written responses to paired isomorphic problems given to introductory physics students and…

MOOCs have the potential to revolutionize higher education with their wide outreach and accessibility, but they require instructors to come up with scalable alternates to traditional student evaluation. Peer grading -- having students…

Curriculum learning--ordering training examples in a sequence to aid machine learning--takes inspiration from human learning, but has not gained widespread acceptance. Static strategies for scoring item difficulty rely on indirect proxy…

Background and Context. The increasing integration of large language models (LLMs) in computing education presents an emerging challenge in understanding how students use LLMs and craft prompts to solve computational tasks. Prior research…

Large Language Models (LLMs) have shown strong performance on programming tasks, but can they generate student-like code like real students - imperfect, iterative, and stylistically diverse? We present ParaStudent, a systematic study of…

Recent studies report that many machine reading comprehension (MRC) models can perform closely to or even better than humans on benchmark datasets. However, existing works indicate that many MRC models may learn shortcuts to outwit these…

We investigate the use of sparse coding and dictionary learning in the context of multitask and transfer learning. The central assumption of our learning method is that the tasks parameters are well approximated by sparse linear…

The activity of design involves the decomposition of problems into subproblems and the development and evaluation of solutions. In many cases, solution development is not done from scratch. Designers often evoke and adapt solutions…

We describe the construction, validation and testing of a concept inventory for an Introduction to Physics of Semiconductors course offered by the department of physics for undergraduate engineering students. By design, this inventory…

We propose novel evaluations for mathematical reasoning capabilities of Large Language Models (LLMs) based on mathematical misconceptions. Our primary approach is to simulate LLMs as a novice learner and an expert tutor, aiming to identify…

Drawing appropriate diagrams is a useful problem solving heuristic that can transform a problem into a representation that is easier to exploit for solving it. One major focus while helping introductory physics students learn effective…

Students often struggle with solving programming problems when learning to code, especially when they have to do it online, with one of the most common disadvantages of working online being the lack of personalized help. This help can be…

Code reasoning is a fundamental capability for large language models (LLMs) in the code domain. It involves understanding and predicting a program's execution behavior, such as determining the output for a given input or whether a specific…

One of the major hurdles toward automatic semantic understanding of computer programs is the lack of knowledge about what constitutes functional equivalence of code segments. We postulate that a sound knowledgebase can be used to…

When assessing student work, graders will often find that some students will leave one or more problems blank on assessments. Since there is no work shown, the grader has no means to evaluate the student's understanding of a particular…

Multi-objective integer or mixed-integer programming problems typically have disconnected feasible domains, making the task of constructing an approximation of the Pareto front challenging. The present paper shows that certain algorithms…

Code super-optimization is the task of transforming any given program to a more efficient version while preserving its input-output behaviour. In some sense, it is similar to the paraphrase problem from natural language processing where the…