4 papers
Safety Alignment of LMs via Non-cooperative Games
Anselm Paulus, Ilia Kulikov, Brandon Amos +4
Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment. Current approaches rely on sequential adversarial trai…
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…
AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?
Ori Press, Brandon Amos, Haoyu Zhao +21
Despite progress in language model (LM) capabilities, evaluations have thus far focused on models' performance on tasks that humans have previously solved, including in programming…
AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs
Anselm Paulus, Arman Zharmagambetov, Chuan Guo +2
Large Language Models (LLMs) are vulnerable to jailbreaking attacks that lead to generation of inappropriate or harmful content. Manual red-teaming requires a time-consuming search…