4 papers
Exploration Hacking: Can LLMs Learn to Resist RL Training?
Eyon Jang, Damon Falck, Joschka Braun +6
Reinforcement learning (RL) has become essential to the post-training of large language models (LLMs) for reasoning, agentic capabilities and alignment. Successful RL relies on suf…
The Impact of Off-Policy Training Data on Probe Generalisation
Nathalie Kirch, Samuel Dower, Adrians Skapars +3
Probing has emerged as a promising method for monitoring large language models (LLMs), enabling cheap inference-time detection of concerning behaviours. However, natural examples o…
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…
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…