cs.CLJul 9, 2026

Role Steering of Language Models for Social Simulations

Authors: Isaac Song, Mohammed Rehan Parwani, Glenn Matlin, Emile Anand, Akhil Theerthala, Arjun Chatterjee, Anthony Wen-Ming Zang, Maria Kostylew, 

Abstract

Social simulations built from language-model agents need role-conditioned behavior that can be checked before agents are placed into a simulated population. We introduce an activation-steering screening workflow for role-conditioned agents: define a role profile, extract a role-specific direction, sweep four steering coefficients, evaluate role-profile alignment, and pass or flag each candidate configuration. On OLMo-3-7B-Instruct, we apply the workflow to a mixed 275-role inventory with 228 role-agnostic questions, GPT-4.1-mini prompted role references, and GPT-4.1-mini judges. We also introduce CastVectors, which receive higher judged role-profile alignment than an assistant-axis directional control from prior persona-vector work, with mean overall scores of 63.2 versus 41.1 across the tested grid. They also preserve high lexical diversity, while the control drops sharply at larger coefficients. The role-level screen is the main contribution: most roles improve as steering increases, but 38 roles decline across all six measured dimensions, showing why simulation builders should choose coefficients per role rather than deploy a uniform high-strength setting. Our code is available at https://github.com/HCAI-Lab-GT/casting-call-vectors, and the role vectors and evaluation data at https://huggingface.co/datasets/HCAI-Lab-GT/casting-call-vectors.

Figures & tables

Appendix figures & tables26 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Investigating Assistant Bias in LLM User Simulators Using a Role Vector

    Sep 1, 2026Daeheon Jeong, Yoonjoo Lee, Eugene Choi +2Large Language Model-Based Role-Play SimulationUser Simulation

  2. AI Agents Alone Are Not (Yet) Sufficient for Social Simulation

    Feb 19, 2026Yiming Li, Dacheng TaoLarge Language Model-Based Social SimulationHuman Behavior Simulation

  3. Thinking Less to Simulate Better: Intuitive Prompting Improves LLM Agents Simulating Individual Social Media Reactions, Including Unfamiliar Content

    Sep 24, 2026Ljubisa Bojic, Tijana Stanic, Joerg Matthes +3Large Language Model-Based Social SimulationUser Simulation