10 papers
Evaluation Awareness in Language Models Has Limited Effect on Behaviour
Amelie Knecht, Lucas Florin, Thilo Hagendorff
Large reasoning models (LRMs) sometimes note in their chain of thought (CoT) that they may be under evaluation. Researchers worry that this verbalised evaluation awareness (VEA) ca…
"Dark Triad" Model Organisms of Misalignment: Narrow Fine-Tuning Mirrors Human Antisocial Behavior
Roshni Lulla, Fiona Collins, Sanaya Parekh +2
The alignment problem refers to concerns regarding powerful intelligences, ensuring compatibility with human preferences and values as capabilities increase. Current large language…
Emergently Misaligned Language Models Show Behavioral Self-Awareness That Shifts With Subsequent Realignment
Laurène Vaugrante, Anietta Weckauff, Thilo Hagendorff
Recent research has demonstrated that large language models (LLMs) fine-tuned on incorrect trivia question-answer pairs exhibit toxicity - a phenomenon later termed "emergent misal…
Speciesism in AI: Evaluating Discrimination Against Animals in Large Language Models
Monika JotautaitÄ, Lucius Caviola, David A. Brewster +1
As large language models (LLMs) become more widely deployed, it is crucial to examine their ethical tendencies. Building on research on fairness and discrimination in AI, we invest…
Large Reasoning Models Are Autonomous Jailbreak Agents
Thilo Hagendorff, Erik Derner, Nuria Oliver
Jailbreaking -- bypassing built-in safety mechanisms in AI models -- has traditionally required complex technical procedures or specialized human expertise. In this study, we show…
On the Inevitability of Left-Leaning Political Bias in Aligned Language Models
Thilo Hagendorff
The guiding principle of AI alignment is to train large language models (LLMs) to be harmless, helpful, and honest (HHH). At the same time, there are mounting concerns that LLMs ex…