4 papers
Agent-Supported Foresight for AI Systemic Risks: AI Agents for Breadth, Experts for Judgment
Leon Fröhling, Alessandro Giaconia, Edyta Paulina Bogucka +1
AI impact assessments often stress near-term risks because human judgment degrades over longer horizons, exemplifying the Collingridge dilemma: foresight is most needed when knowle…
Political Ideology Shifts in Large Language Models
Pietro Bernardelle, Stefano Civelli, Leon Fröhling +3
Large language models (LLMs) are increasingly deployed in politically sensitive settings, raising concerns about their potential to encode, amplify, or be steered toward specific i…
Mapping and Influencing the Political Ideology of Large Language Models using Synthetic Personas
Pietro Bernardelle, Leon Fröhling, Stefano Civelli +3
The analysis of political biases in large language models (LLMs) has primarily examined these systems as single entities with fixed viewpoints. While various methods exist for meas…
Personas with Attitudes: Controlling LLMs for Diverse Data Annotation
Leon Fröhling, Gianluca Demartini, Dennis Assenmacher
We present a novel approach for enhancing diversity and control in data annotation tasks by personalizing large language models (LLMs). We investigate the impact of injecting diver…