Goto

Collaborating Authors







Many-shot Jailbreaking

Neural Information Processing Systems

Longer contexts present a new attack surface for adversarial attacks. In search of a "fruit-fly" of long-context vulnerabilities, we study Many-shot Jailbreaking (MSJ; Figure 1), a simple yet effective and scalable jailbreak.


SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain

Neural Information Processing Systems

The integration of synthetically generated data in the second and third steps enhances the models' capabilities in interpreting and processing legal texts, effectively reaching state-of-the-art performance and outperforming