SOURCE-LINKED INTELLIGENCE

Interpreting and Steering LLM Agents for Social Simulations

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Simulations based on large language models (LLMs) have proven to be powerful for understanding human behavior, making them valuable additions to the social scientific toolkit. However, LLMs are ultimately black boxes based on deep neural networks which limits their value for social science. This is because of a lack of (i) interpretability: i.e. the ability to assign clear mechanisms driving observed behavior; and a lack of (ii) steerability: i.e. the ability to mute or amplify specific theoretically meaningful mechanisms of action to drive specific model behavior. Here, we demonstrate how the

Read original source ↗ Open in workspace

recordType

paper

region

Global