← Search

Junyi Tao

2 accepted papers

2025

Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors

ICML 2025poster

Interpretability research now offers a variety of techniques for identifying abstract internal mechanisms in neural networks. Can such techniques be used to predict how models will behave on out-of-distribution examples? In this work, we provide a positive answer to this question. Through a diverse…

2024

Inference and Verbalization Functions During In-Context Learning

EMNLP 2024finding

Large language models (LMs) are capable of in-context learning from a few demonstrations (example-label pairs) to solve new tasks during inference. Despite the intuitive importance of high-quality demonstrations, previous work has observed that, in some settings, ICL performance is minimally affecte…