2 citations · 3 across the 4 of their papers we have counts for
5 papers
Can CaMeLs Talk? Securing Multi-Agent Systems Against Indirect Prompt Injection Attacks
James Peters-Gill, Avi Semler, Henning Bartsch +2
Indirect prompt injection attacks - malicious instructions embedded in content processed by large language models - remain a major obstacle to safely deploying tool-using agents. C…
Removing Sandbagging in LLMs by Training with Weak Supervision
Emil Ryd, Henning Bartsch, Julian Stastny +2
As AI systems begin to automate complex tasks, supervision increasingly relies on weaker models or limited human oversight that cannot fully verify output quality. A model more cap…
Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI
Sharan Maiya, Henning Bartsch, Nathan Lambert +1
The character of the "AI assistant" persona generated by modern chatbot large language models influences both surface-level behavior and apparent values, beliefs, and ethics. These…
Self-Consistency of Large Language Models under Ambiguity
Henning Bartsch, Ole Jorgensen, Domenic Rosati +2
Large language models (LLMs) that do not give consistent answers across contexts are problematic when used for tasks with expectations of consistency, e.g., question-answering, exp…
Learning to Request Guidance in Emergent Communication
Benjamin Kolb, Leon Lang, Henning Bartsch +6
Previous research into agent communication has shown that a pre-trained guide can speed up the learning process of an imitation learning agent. The guide achieves this by providing…