From Plausible to Causal: Counterfactual Semantics for Policy Evaluation in Simulated Online Communities

Agam Goyal, Yian Wang, Eshwar Chandrasekharan, Hari Sundaram

Keywords: LLM Social Simulations, Policy Interventions, Online Community Governance

Abstract: LLM-based social simulations can generate believable community interactions, enabling "policy wind tunnels" where governance interventions are tested before deployment. But believability is not causality. Claims like "intervention A reduces escalation" require causal semantics that current simulation work lacks. We propose adopting the causal counterfactual framework, distinguishing *necessary causation* (would the outcome have occurred without the intervention?) from *sufficient causation* (does the intervention reliably produce the outcome?). This distinction maps onto different stakeholder needs: moderators diagnosing incidents require necessary causation, while platform designers choosing policies require sufficient causation. We formalize this mapping, show how simulation's design properties satisfy assumptions for causal estimation. Finally, we argue that regardless of current simulator limitations, establishing this framework now is essential as it can help define what adequate fidelity means and moves the field from simulations that look real toward simulations that inform real, policy-relevant decisions.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 16