Related papers: Pedagogical learning
We study subliminal learning, a surprising phenomenon where language models transmit behavioral traits via semantically unrelated data. In our main experiments, a "teacher" model with some trait T (such as liking owls or being misaligned)…
Recently, the concept of teaching has been introduced into machine learning, in which a teacher model is used to guide the training of a student model (which will be used in real tasks) through data selection, loss function design, etc.…
Modern machine learning models are opaque, and as a result there is a burgeoning academic subfield on methods that explain these models' behavior. However, what is the precise goal of providing such explanations, and how can we demonstrate…
It is well known that ensemble methods often provide enhanced performance in reinforcement learning. In this paper, we explore this concept further by using group-aided training within the distributional reinforcement learning paradigm.…
Machine Teaching (MT) is an interactive process where humans train a machine learning model by playing the role of a teacher. The process of designing an MT system involves decisions that can impact both efficiency of human teachers and…
We study the problem of computer-assisted teaching with explanations. Conventional approaches for machine teaching typically only provide feedback at the instance level e.g., the category or label of the instance. However, it is intuitive…
We consider a setting where a population of artificial learners is given, and the objective is to optimize aggregate measures of performance, under constraints on training resources. The problem is motivated by the study of peer learning in…
Science consists on conceiving hypotheses, confronting them with empirical evidence, and keeping only hypotheses which have not yet been falsified. Under deductive reasoning they are conceived in view of a theory and confronted with…
While Multiple Instance (MI) data are point patterns -- sets or multi-sets of unordered points -- appropriate statistical point pattern models have not been used in MI learning. This article proposes a framework for model-based MI learning…
Synthetic data has been widely used to train large language models, but their generative nature inevitably introduces noisy, non-informative, and misleading learning signals. In this paper, we propose Montessori-Instruct, a novel data…
Teaching an agent to perform new tasks using natural language can easily be hindered by ambiguities in interpretation. When a teacher provides an instruction to a learner about an object by referring to its features, the learner can…
Large language models are able to perform a task by conditioning on a few input-output demonstrations - a paradigm known as in-context learning. We show that language models can explicitly infer an underlying task from a few demonstrations…
It is incredibly easy for a system designer to misspecify the objective for an autonomous system ("robot''), thus motivating the desire to have the robot learn the objective from human behavior instead. Recent work has suggested that people…
Machines, not humans, are the world's dominant knowledge accumulators but humans remain the dominant decision makers. Interpreting and disseminating the knowledge accumulated by machines requires expertise, time, and is prone to failure.…
For many years, researchers in psychology, education, statistics, and machine learning have been developing practical methods to improve learning speed, retention, and generalizability, and this work has been successful. Many of these…
Machine learning algorithms learn to solve a task, but are unable to improve their ability to learn. Meta-learning methods learn about machine learning algorithms and improve them so that they learn more quickly. However, existing…
Inspired by human learning, researchers have proposed ordering examples during training based on their difficulty. Both curriculum learning, exposing a network to easier examples early in training, and anti-curriculum learning, showing the…
Artificial intelligence is to teach machines to take actions like humans. To achieve intelligent teaching, the machine learning community becomes to think about a promising topic named machine teaching where the teacher is to design the…
Large neural networks trained in the overparameterized regime are able to fit noise to zero train error. Recent work \citep{nakkiran2020distributional} has empirically observed that such networks behave as "conditional samplers" from the…
Successful teaching entails a complex interaction between a teacher and a learner. The teacher must select and convey information based on what they think the learner perceives and believes. Teaching always involves misaligned beliefs, but…