相关论文: Can metacognition predict your success in solving …

Computation, the use of a computer to solve, simulate, or visualize a physical problem, has revolutionized how physics research is done. Computation is used widely to model systems, to simulate experiments, and to analyze data. Yet, in most…

Programming digital devices and developing software is an important professional qualification, which contributes to employment opportunities. Despite this fact, there is a remarkable shortage in suitable human resources. In this context,…

The deployment of pre-trained perception models in novel environments often leads to performance degradation due to distributional shifts. Although recent artificial intelligence approaches for metacognition use logical rules to…

Predictions in the social world generally influence the target of prediction, a phenomenon known as performativity. Self-fulfilling and self-negating predictions are examples of performativity. Of fundamental importance to economics,…

Learning good representations of historical contexts is one of the core challenges of reinforcement learning (RL) in partially observable environments. While self-predictive auxiliary tasks have been shown to improve performance in fully…

Curiosity is a vital metacognitive skill in educational contexts. Yet, little is known about how social factors influence curiosity in group work. We argue that curiosity is evoked not only through individual, but also interpersonal…

Code completion is a popular software development tool integrated into all major IDEs. Many neural language models have achieved promising results in completion suggestion prediction on synthetic benchmarks. However, a recent study When…

As programmers write code, they often edit and retry multiple times, creating rich "interaction traces" that reveal how they approach coding tasks and provide clues about their level of skill development. For novice programmers in…

Deficits in working memory, which includes both the ability to learn and to retain information short-term, are a hallmark of many cognitive disorders. Our study analyzes data from a neuroscience experiment on animal subjects, where…

This comprehensive report distinguishes prior works by the cognitive functions they innovate. Many works claim an almost "human-like" cognitive capability in their world models. To evaluate these claims requires a proper grounding in first…

The computing education community has a rich history of pedagogical innovation designed to support students in introductory courses, and to support teachers in facilitating student learning. Very recent advances in artificial intelligence…

Instructional designers face an overwhelming array of design choices, making it challenging to identify the most effective interventions. To address this issue, I propose the concept of a Model Human Learner, a unified computational model…

Research on intelligent tutoring systems has been exploring data-driven methods to deliver effective adaptive assistance. While much work has been done to provide adaptive assistance when students seek help, they may not seek help…

Measuring performance & quantifying a performance change are core evaluation techniques in programming language and systems research. Of 122 recent scientific papers, as many as 65 included experimental evaluation that quantified a…

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…

In several papers published in Biological Cybernetics in the 1980s and 1990s, Kawato and colleagues proposed computational models explaining how internal models are acquired in the cerebellum. These models were later supported by…

In this paper we will discuss metalearning and how we can go beyond the current classical learning paradigm. We will first address the importance of inductive biases in the learning process and what is at stake: the quantities of data…

Machine learning models are often used to inform real world risk assessment tasks: predicting consumer default risk, predicting whether a person suffers from a serious illness, or predicting a person's risk to appear in court. Given…

The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings. Prior work has identified test-time contextual cues, such as hypothetical scenarios, as a source of verbalized…

In-context learning enables large language models to perform novel tasks through few-shot demonstrations. However, demonstrations per se can naturally contain noise and conflicting examples, making this capability vulnerable. To understand…