All developed resources are publicly available on HuggingFace under a single collection: huggingface.co/collections/.... Our code is available at: github.com/coastalcph/p... [The End] 5/5

Lastly, we conduct a small-scale OOD exploratory evaluation using European political speeches. RoBERTa’s performance severely drops due to overfitting, while Qwen 3 and Gemini 2.5 achieve comparable results and outperform RoBERTa by ~10%, showcasing robustness across domains. 4/5

Our analysis of a large collection of Trump’s campaign speeches (2015 -2025) reveals: (a) a decline in populist rhetoric over time, (b) no meaningful difference in populist intensity between swing/non-swing states, and (c) populism is concentrated towards the end of a speech. 3/5

We examine whether LLMs can identify and classify fine-grained forms of populism, a complex and contested concept in both academic and media debates. To this end, we curate and release datasets and evaluate a range of large language models across multiple prompting paradigms. 2/5

My research will center on three key areas: (a) NLP for Political Science, (b) AI & Society, beginning with critical challenges in AI alignment, and (c) NLP for Law.

Reach out if you're interested in any of the above 👆
I'm glad to share more and listen to your ideas 😇 2/2

In short, the Llama 4 System Prompt is 101 the mantra of Trump vol. 2; heavily concentrated around "anti-wokeness" and "freedom of speech" at all costs. 2/2