🙌 OpenHands: AI-Driven Development

Official code for "Measuring Non-Adversarial Reproduction of Training Data in Large Language Models" (https://arxiv.org/abs/2411.10242)

Official repository for the paper "Gradient-based Jailbreak Images for Multimodal Fusion Models" (https//arxiv.org/abs/2410.03489)

Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".

Approximation of the Claude 3 tokenizer by inspecting generation stream

Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"

Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.