PAIR.withgoogle.com and friend's work on interpretability methods

The dataset and code for the ICLR 2024 paper "Can LLM-Generated Misinformation Be Detected?"

"Exploring Concept Depth: How Large Language Models Acquire Knowledge at Different Layers?"

Probing language models for linguistic features in their representations

LLM vulnerability scanner

code release for the paper "On Completeness-aware Concept-Based Explanations in Deep Neural Networks"

Model interpretability and understanding for PyTorch

A curated list of Large Language Model (LLM) Interpretability resources.

Official repository for ``Concept-based Interpretation Without Linear Assumption'' published in ICLR 2023.

EMNLP 2024: Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue

[ICML 2024] "Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models"

LLM-Merging: Building LLMs Efficiently through Merging

Official pytorch implementation of "Interpreting the Second-Order Effects of Neurons in CLIP"

Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts

Training Sparse Autoencoders on Language Models

Improving Alignment and Robustness with Circuit Breakers

A Collection of Variational Autoencoders (VAE) in PyTorch.

A simple tutorial of Variational AutoEncoders with Pytorch

Mutual Information in Pytorch

This is an implementation of the VAE (Variational Autoencoder) for Cifar10

Inference-Time Intervention: Eliciting Truthful Answers from a Language Model

Repository for PrimeVul Vulnerability Detection Dataset

DiverseVul: A New Vulnerable Source Code Dataset for Deep Learning Based Vulnerability Detection (RAID 2023) https://surrealyz.github.io/files/pubs/raid23-diversevul.pdf

RAI Games