Large language models offer opportunities to simulate multi-party deliberation, but realistic modeling remains limited by a lack of speaker-attributed data. Transcripts produced via automatic speech recognition (ASR) assign anonymous speaker labels (e.g., Speaker_1), preventing models from capturing consistent human behavior. This work introduces a reproducible pipeline to transform public Zoom recordings into speaker-attributed transcripts with metadata like persona profiles and pragmatic action tags (e.g., [propose_motion]). We release three local government deliberation datasets: Appellate Court hearings, School Board meetings, and Municipal Council sessions. Fine-tuning LLMs to model specific participants using this "action-aware" data produces a 67% reduction in perplexity and nearly doubles classifier-based performance metrics for speaker fidelity and realism. Turing-style human evaluations show our simulations are often indistinguishable from real deliberations, providing a practical and scalable method for complex realistic civic simulations.
@article{arxiv.2511.17813,
title = {Point of Order: Action-Aware LLM Persona Modeling for Realistic Civic Simulation},
author = {Scott Merrill and Shashank Srivastava},
journal= {arXiv preprint arXiv:2511.17813},
year = {2026}
}
Comments
8 pages (32 pages including appendix), 18 figures. Code and datasets are available at https://github.com/smerrillunc/action-aware-llms. Submitted to ACL 2026