2 papers
cs.CY2026
Auditing Alignment Controllability in LLMs via Political Axes
Bartol Bućan, Nikola Sočec, Sarah Isufi +5
Political audits of large language models (LLMs) usually reduce each to one point on a political compass. But that resting point barely matters in deployment: a model must land som…
cs.CY2022
Prismal view of ethics
Sarah Isufi, Kristijan Poje, Igor Vukobratovic +1
We shall have a hard look at ethics and try to extract insights in the form of abstract properties that might become tools. We want to connect ethics to games, talk about the perfo…