Ryan Liu

Large Language Models Develop Novel Social Biases Through Adaptive Exploration

Evaluating Language Models' Evaluations of Games

Accumulating Context Changes the Beliefs of Language Models

Are Large Language Models Sensitive to the Motives Behind Communication?

Large Language Models Assume People are More Rational than We Really are

RLHS: Mitigating Misalignment in RLHF with Hindsight Simulation

Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse

Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse