SLALOM: Solving the 'Stopped Clock' Problem in LLM Social Simulations via Trajectory Validation
arXiv·low signal
Lee and Seering present SLALOM, a framework addressing the 'stopped clock' problem in LLM-based social simulations: current evaluation confirms correct final outcomes while ignoring whether the trajectory was sociologically plausible. Because LLM reasoning is opaque, verifying that social mechanisms operate correctly — not just that endpoints match — requires longitudinal observation metrics. For builders using LLM agents to model social dynamics or user behavior, this provides the first trajectory-aware validation methodology.