llm-safety topic

Attack to induce LLMs within hallucinations

PKU-YuanGroup

Restore safety in fine-tuned language models through task arithmetic

declare-lab

Papers about red teaming LLMs and Multimodal models.

Libr-AI

Official repository for the paper "ALERT: A Comprehensive Benchmark for Assessing Large Language Models’ Safety through Red Teaming"

Babelscape

Code and dataset for the paper: "Can Editing LLMs Inject Harm?"

llm-editing