Author

Mario Brcic

University of Zagreb Faculty of Electrical Engineering and Computing

h-index 12 Homepage View on Semantic Scholar

We have 1 of 51 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#large language models Jul 2026

Auditing Alignment Controllability in LLMs via Political Axes

A dispersion-first stress test of prompt-based controllability across 12 ideological personas plus an unsteered baseline, 70 Political Compass items, ten replicates, and seven leading LLMs: GPT-5, Claude, Grok, Gemini, DeepSeek, Kimi, and Qwen.

Bartol Bućan, Nikola Sočec, Sarah Isufi et al. · arXiv.org · 0 citations