Related papers: Are Self-explaining and Coached Problem Solving Mo…
Language Models (LMs) can perform new tasks by adapting to a few in-context examples. For humans, explanations that connect examples to task principles can improve learning. We therefore investigate whether explanations of few-shot examples…
Our research demonstrates the significant benefits of using fine-tuning with explanations to enhance the performance of language models. Unlike prompting, which maintains the model's parameters, fine-tuning allows the model to learn and…
Can a model learn to escape its own learning plateau? Reinforcement learning methods for finetuning large reasoning models stall on datasets with low initial success rates, and thus little training signal. We investigate a fundamental…
Social dilemmas have been widely studied to explain how humans are able to cooperate in society. Considerable effort has been invested in designing artificial agents for social dilemmas that incorporate explicit agent motivations that are…
Robots should be able to learn complex behaviors from human demonstrations. In practice, these human-provided datasets are inevitably imbalanced: i.e., the human demonstrates some subtasks more frequently than others. State-of-the-art…
Collective or group intelligence is manifested in the fact that a team of cooperating agents can solve problems more efficiently than when those agents work in isolation. Although cooperation is, in general, a successful problem solving…
The act of explaining across two parties is a feedback loop, where one provides information on what needs to be explained and the other provides an explanation relevant to this information. We apply a reinforcement learning framework which…
Pair programming is widely recognized as an effective educational tool in computer science that promotes collaborative learning and mirrors real-world work dynamics. However, communication breakdowns within pairs significantly challenge…
Action advising is a knowledge transfer technique for reinforcement learning based on the teacher-student paradigm. An expert teacher provides advice to a student during training in order to improve the student's sample efficiency and…
How is it that humans can solve complex planning tasks so efficiently despite limited cognitive resources? One reason is its ability to know how to use its limited computational resources to make clever choices. We postulate that people…
People frequently face challenging decision-making problems in which outcomes are uncertain or unknown. Artificial intelligence (AI) algorithms exist that can outperform humans at learning such tasks. Thus, there is an opportunity for AI…
Artificial intelligence is increasingly embedded in education, raising a fundamental question: when learners use AI, does it support their thinking or replace it? While existing research has focused on system capabilities and challenges and…
Can artificial agents benefit from human conventions? Human societies manage to successfully self-organize and resolve the tragedy of the commons in common-pool resources, in spite of the bleak prediction of non-cooperative game theory. On…
We are interested in better understanding ways that students collaborate to solve conceptual physics problems in the context of spherical unit vectors in upper-level E&M, especially problems that have been shown to be difficult for students…
We describe a study in which introductory physics students engage in reflection with peers about problem solving. The recitations for an introductory physics course with 200 students were broken into the "Peer Reflection" (PR) group and the…
We show that the ability to lead groups of humans is predicted by leadership skill with Artificially Intelligent agents. In a large pre-registered lab experiment, human leaders worked with AI agents to solve problems. Their performance on…
Academic performance is perceived as a product of complex interactions between students' overall experience, personal characteristics and upbringing. Data science techniques, most commonly involving regression analysis and related…
Inferring the abstract relational and causal structure of the world is a major challenge for reinforcement-learning (RL) agents. For humans, language--particularly in the form of explanations--plays a considerable role in overcoming this…
The main approach to evaluating communication is by assessing how well it facilitates coordination. If two or more individuals can coordinate through communication, it is generally assumed that they understand one another. We investigate…
Skills are temporal abstractions that are intended to improve reinforcement learning (RL) performance through hierarchical RL. Despite our intuition about the properties of an environment that make skills useful, a precise characterization…