41 citations · 68 across the 24 of their papers we have counts for
7 papers · 1 filter
AdvPrefix: An Objective for Nuanced LLM Jailbreaks
Sicheng Zhu, Brandon Amos, Yuandong Tian +2
Many jailbreak attacks on large language models (LLMs) rely on a common objective: making the model respond with the prefix ``Sure, here is (harmful request)''. While straightforwa…
LLäMmlein: Transparent, Compact and Competitive German-Only Language Models from Scratch
Jan Pfister, Julia Wunderle, Andreas Hotho
We create two German-only decoder models, LLäMmlein 120M and 1B, transparently from scratch and publish them, along with the training data, for the German NLP research community to…
Gradient-based Jailbreak Images for Multimodal Fusion Models
Javier Rando, Hannah Korevaar, Erik Brinkman +2
Augmenting language models with image inputs may enable more effective jailbreak attacks through continuous optimization, unlike text inputs that require discrete optimization. How…
Persistent Pre-Training Poisoning of LLMs
Yiming Zhang, Javier Rando, Ivan Evtimov +5
Large language models are pre-trained on uncurated text datasets consisting of trillions of tokens scraped from the Web. Prior work has shown that: (1) web-scraped pre-training dat…
Automated Red Teaming with GOAT: the Generative Offensive Agent Tester
Maya Pavlova, Erik Brinkman, Krithika Iyer +7
Red teaming assesses how large language models (LLMs) can produce content that violates norms, policies, and rules set during their safety training. However, most existing automate…
The Llama 3 Herd of Models
Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri +556
Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It is a herd of language models th…
Towards Red Teaming in Multimodal and Multilingual Translation
Christophe Ropers, David Dale, Prangthip Hansanti +9
Assessing performance in Natural Language Processing is becoming increasingly complex. One particular challenge is the potential for evaluation datasets to overlap with training da…