6 papers
Instruction-Conditioned Exploration for Reinforcement Learning with Self-Distillation to an Unconditioned Policy
Jim Dilkes, Vahid Yazdanpanah, Sebastian Stein
Post-training Large Language Models (LLMs) with Reinforcement Learning (RL) has become an important tool for improving model capabilities, but the LLM action-space structure introd…
Three Lessons from Citizen-Centric Participatory AI Design
Eike Schneiders, Sarah Kiden, Beining Zhang +5
This workshop paper examines challenges in designing agentic AI systems from a citizen-centric perspective. Drawing on three participatory workshops conducted in 2025 with members…
Back to the Communities: A Mixed-Methods and Community-Driven Evaluation of Cultural Sensitivity in Text-to-Image Models
Sarah Kiden, Oriane Peter, Gisela Reyes-Cruz +11
Evidence shows that text-to-image (T2I) models disproportionately reflect Western cultural norms, amplifying misrepresentation and harms to minority groups. However, evaluating cul…
PTFA: An LLM-based Agent that Facilitates Online Consensus Building through Parallel Thinking
Wen Gu, Zhaoxing Li, Jan Buermann +5
Consensus building is inherently challenging due to the diverse opinions held by stakeholders. Effective facilitation is crucial to support the consensus building process and enabl…
Reinforced Language Models for Sequential Decision Making
Jim Dilkes, Vahid Yazdanpanah, Sebastian Stein
Large Language Models (LLMs) show potential as sequential decision-making agents, but their application is often limited due to a reliance on large, computationally expensive model…
Responsible AI Governance: A Response to UN Interim Report on Governing AI for Humanity
Sarah Kiden, Bernd Stahl, Beverley Townsend +22
This report presents a comprehensive response to the United Nation's Interim Report on Governing Artificial Intelligence (AI) for Humanity. It emphasizes the transformative potenti…