3 citations · 3 across the 4 of their papers we have counts for
Showing 2024Show all
2 papers · 1 filter
cs.CY2024★ 3 cited
TRIAGE: Ethical Benchmarking of AI Models Through Mass Casualty Simulations
Nathalie Maria Kirch, Konstantin Hebenstreit, Matthias Samwald
We present the TRIAGE Benchmark, a novel machine ethics (ME) benchmark that tests LLMs' ability to make ethical decisions during mass casualty incidents. It uses real-world ethical…
cs.CR2024
What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind Attacks
Nathalie Kirch, Constantin Weisser, Severin Field +2
Jailbreaks have been a central focus of research regarding the safety and reliability of large language models (LLMs), yet the mechanisms underlying these attacks remain poorly und…