Yann Vonlanthen — accepted AI-conference papers

2026

Reasoning Boosts Opinion Alignment in LLMs

Frédéric Berdoz, Yann Billeter, Yann Vonlanthen, Roger Wattenhofer

ICLR 2026poster

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 policies. Given their versatility, strong generalization capabilities, and demonstrated success across diverse text-to-…

Cited by 0 Source ↗code ↗Scholar ↗

2025

Recommender Systems for Democracy: Toward Adversarial Robustness in Voting Advice Applications

Frédéric Berdoz, Dustin Brunner, Yann Vonlanthen, Roger Wattenhofer

IJCAI 2025

Voting advice applications (VAAs) help millions of voters understand which political parties or candidates best align with their views. This paper explores the potential risks these applications pose to the democratic process when targeted by adversarial entities. In particular, we expose 11 manipul

Cited by 0 Source ↗PDF ↗Scholar ↗