• A Moral Agency Framework for Legitimate Integration of AI in Bureaucracies

  With Joanna Bryson. Abstract in Proceedings of AIES 2025; to appear in Public Administration and Emerging Technologies, Edward Elgar Publishing.

  2026

• Agent Benchmarks Fail Public-Sector Requirements

  With Jonathan Rystrom, Karolina Korgul, Jan Batzner, and Chris Russell. To appear in Proceedings of IASEAI 2026.

  2026

• Measuring what Matters: Construct Validity in Large Language Model Benchmarks

  Andrew Bean et al. In Proceedings of NeurIPS 2025 Datasets & Benchmarks Track.

  2025

• Oversight Structures for Agentic AI in Public-Sector Institutions

  With Jonathan Rystrom and Jan Batzner. In Proceedings of REALM@ACL 2025.

  2025