Aberdeen, UK

Ruizhe Li

Expert
@ruizheliUOA

Working on NLP/NLG/ML.

www.ruizhe.space/

Awesome-Interpretability-in-Large-Language-Models. This repository collects all relevant resources about interpretability in LLMs

402

HR-VAE. Code for the paper "A Stable Variational Autoencoder for Text Modelling"

26

ARC_JSD. A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation

15

TWR-VAE. Improving Variational Autoencoder for Text Modelling withTimestep-Wise Regularisation

5

Anchored_Bias_GPT2. This is the official code for anchored bias of GPT2

4
5
Apply