Chenhao Tan

Executable Counterfactuals: Improving LLMs' Causal Reasoning Through Code

Why Can't Transformers Learn Multiplication? Reverse-Engineering Implicit Chain-of-Thought Reveals Challenges of Learning Long-Range Dependencies

Know Thyself? On the Incapability and Implications of AI Self-Recognition

On the Effectiveness and Generalization of Race Representations for Debiasing High-Stakes Decisions

Concept Incongruence: An Exploration of Time and Death in Role Playing

Causal Abstraction Finds Universal Representation of Race in Large Language Models