Picture for Kevin Baum

Kevin Baum

Saarland University, Germany

Soft Begging: Modular and Efficient Shielding of LLMs against Prompt Injection and Jailbreaking based on Prompt Tuning

Add code
Jul 03, 2024
Viaarxiv icon

Software Doping Analysis for Human Oversight

Add code
Aug 11, 2023
Viaarxiv icon

What Do We Want From Explainable Artificial Intelligence ? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research

Add code
Feb 15, 2021
Figure 1 for What Do We Want From Explainable Artificial Intelligence ? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research
Figure 2 for What Do We Want From Explainable Artificial Intelligence ? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research
Viaarxiv icon

Towards a Framework Combining Machine Ethics and Machine Explainability

Add code
Jan 03, 2019
Figure 1 for Towards a Framework Combining Machine Ethics and Machine Explainability
Figure 2 for Towards a Framework Combining Machine Ethics and Machine Explainability
Viaarxiv icon