Jiaxin Wen

Unsupervised-Elicitation. Python

MisleadLM. Official Code for our paper: "Language Models Learn to Mislead Humans via RLHF""

GDsuite. A toy eval suite for tracing generalization dynamics of LM pre-training

storyboard.

Introduction-to-Machine-Learning. Python

mend. MEND: Fast Model Editing at Scale