3 papers
cs.CL2026
Reasoning Boosts Opinion Alignment in LLMs
Frédéric Berdoz, Yann Billeter, Yann Vonlanthen +1
Opinion modeling aims to capture individual or group political preferences, enabling applications such as digital democracies, where models could help shape fairer and more popular…
astro-ph.GA2025
Galactic Alchemy: Deep Learning Map-to-Map Translation in Hydrodynamical Simulations
Philipp Denzel, Yann Billeter, Frank-Peter Schilling +1
We present the first systematic study of multi-domain map-to-map translation in galaxy formation simulations, leveraging deep generative models to predict diverse galactic properti…
cs.CL2023
Exploring the Jungle of Bias: Political Bias Attribution in Language Models via Dependency Analysis
David F. Jenny, Yann Billeter, Mrinmaya Sachan +2
The rapid advancement of Large Language Models (LLMs) has sparked intense debate regarding the prevalence of bias in these models and its mitigation. Yet, as exemplified by both re…