Simulating Policy Discussions with Digital Footprints and Large Language Models

Published in International Journal of Population Data Science, 2025

Recommended citation: Meng, W., Harvey, J., Carter, C., Nica-Avram, G., Goulding, J., Frobisher, P., Forrest, M. and N/A (2025) “Simulating Policy Discussions with Digital Footprints and Large Language Models”, International Journal of Population Data Science, 10(5). doi: 10.23889/ijpds.v10i5.3328. https://doi.org/10.23889/ijpds.v10i5.3328

Highlights

  • This study explores the potential of LLMs to simulate UK par- liamentary debates, with a focus on speaker roles and stance- taking.
  • Initial results suggest that LLMs can reproduce key ele- ments of real parliamentary debates, offering a promising step toward simulating more complex, multi-actor policy dialogues

Download paper here Download poster here