Noah Goodman

Language and Experience: A Computational Model of Social Learning in Complex Tasks

Belief Dynamics Unify In-Context Learning and Activation Steering

Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs

What Makes a Maze Look Like a Maze?

Eliciting Human Preferences with Language Models

In-Context Learning Strategies Emerge Rationally

From Next-Token to Mathematics: The Learning Dynamics of Mathematical Reasoning in Language Models

Bayesian scaling laws for in-context learning

Bayesian scaling laws for in-context learning

D3: A Dataset for Training Code LMs to Act Diff-by-Diff

MathCAMPS: Fine-grained Synthesis of Mathematical Problems From Human Curricula

Emergent Symbol-Like Number Variables in Artificial Neural Networks

CALM: Critic Automation with Language Models