611 citations · 711 across the 9 of their papers we have counts for
Showing 2024Show all
2 papers · 1 filter
cs.CR2024
Soft Begging: Modular and Efficient Shielding of LLMs against Prompt Injection and Jailbreaking based on Prompt Tuning
Simon Ostermann, Kevin Baum, Christoph Endres +2
Prompt injection (both direct and indirect) and jailbreaking are now recognized as significant issues for large language models (LLMs), particularly due to their potential for harm…
cs.CY2024★ 74 cited
On the Quest for Effectiveness in Human Oversight: Interdisciplinary Perspectives
Sarah Sterz, Kevin Baum, Sebastian Biewer +4
Human oversight is currently discussed as a potential safeguard to counter some of the negative aspects of high-risk AI applications. This prompts a critical examination of the rol…