Related papers: Online administration of a reasoning inventory in …

Temporal reasoning over tabular data presents substantial challenges for large language models (LLMs), as evidenced by recent research. In this study, we conduct a comprehensive analysis of temporal datasets to pinpoint the specific…

Following the emergence of COVID-19 in Spring 2020, undergraduate in-person physics laboratory courses at a R1 public university were adapted for remote learning to accommodate the subsequent campus closure. Video lectures and web-based…

Process Reward Models (PRMs) have recently emerged as a powerful framework for supervising intermediate reasoning steps in large language models (LLMs). Previous PRMs are primarily trained on model final output responses and struggle to…

This paper examines the impact of COVID-19 induced campus closure on university students' self-regulated learning behavior by analyzing click-stream data collected from student interactions with 70 online learning modules in a university…

Large Language Models (LLMs) have demonstrated remarkable performance on various quantitative reasoning and knowledge benchmarks. However, many of these benchmarks are losing utility as LLMs get increasingly high scores, despite not yet…

As a paradigm for sequential decision making in unknown environments, reinforcement learning (RL) has received a flurry of attention in recent years. However, the explosion of model complexity in emerging applications and the presence of…

Reinforcement learning (RL) has become a promising paradigm for optimizing Retrieval-Augmented Generation (RAG) in complex reasoning tasks. However, traditional outcome-based RL approaches often suffer from reward sparsity and inefficient…

Recent advances in reinforcement learning (RL) have significantly improved the complex reasoning capabilities of large language models (LLMs). Despite these successes, existing methods mainly focus on single-domain RL (e.g., mathematics)…

Scientific argumentation is a core science and engineering practice and a necessary 21st Century workforce skill. Due to the nature of large enrollment classes, it is difficult to individually assess students and provide feedback on their…

Calls to transform introductory college physics courses to include scientific practices require assessments that can measure the extent to which these transformations are effective. Such assessments should be able to measure students'…

This work is about making decisions by digital means. Funds should be distributed by the students of Heinrich-Heine-University. The proposals were made by the students themselves without further influence. For this purpose, dialog-based…

The Physics Lab Inventory of Critical Thinking (PLIC) measures three components of students' critical thinking in physics labs: evaluating data, evaluating methods, and proposing next steps. Prior work has analyzed these components in…

Educators have faced new challenges in effective course assessment during the recent, unprecedented shift to remote online learning during the COVID-19 pandemic. In place of typical proctored, timed exams, instructors must now rethink their…

This survey paper chronicles the evolution of evaluation in multimodal artificial intelligence (AI), framing it as a progression of increasingly sophisticated "cognitive examinations." We argue that the field is undergoing a paradigm shift,…

The COVID-19 pandemic has represented a challenge for higher education in terms to provide quality education despite the lockdown periods, the transformation of the in-person classes to virtual classes, and the demotivation and anxiety that…

The world has transitioned into a new phase of online learning in response to the recent Covid19 pandemic. Now more than ever, it has become paramount to push the limits of online learning in every manner to keep flourishing the education…

Although online education has become a viable and major component of higher education in many fields, its employment in engineering disciplines has been limited. COVID-19 pandemic compelled the global and abrupt conversion of conventional…

Understanding scientific papers requires more than answering isolated questions or summarizing content. It involves an integrated reasoning process that grounds textual and visual information, interprets experimental evidence, synthesizes…

While long Chain-of-Thought (CoT) distillation effectively transfers reasoning capability to smaller language models, the reasoning process often remains redundant and computational budget uncontrollable, leading to inefficient resource…

During the wake of the Covid-19 pandemic, the educational paradigm has experienced a major change from in person learning traditional to online platforms. The change of learning convention has impacted the teacher-student especially in…