What People Almost Did: Evaluating LLM Social Simulations Beyond Behavioral Fit
TL;DR
This paper proposes representational adequacy as a new evaluation target for LLM-based social simulations, distinguishes representational adequacy from interpretability and alignment metrics, proposes ways to integrate it into simulation research, and poses its measurement as an open problem.
Abstract
LLM-based social simulations are primarily evaluated for behavioral fit, testing whether agents reproduce the actions or response distributions of the people they are simulating. However, the promise of simulation extends beyond behavioral fit. Simulations can explain human behavior, diagnose barriers, and compare large-scale interventions. These use cases depend on understanding \textit{why} people acted a certain way, not just \textit{what} they did. As a result, behavioral fit is insufficient for these types of claims because behavior underdetermines the reasoning process behind it. For instance, the behavior of staying silent may be due to disinterest or suppressed speech, and not answering a call may be due to distrust of the caller or limited phone access. In this paper, we propose \textit{representational adequacy} as a new evaluation target for LLM-based social simulations. By leveraging LLM reasoning traces, representational adequacy measures whether a simulation's scenario--reasoning--action triples preserve the reasoning process behind the behavior in a way that is faithful to the population and scenarios being simulated. We distinguish representational adequacy from interpretability and alignment metrics, propose ways to integrate it into simulation research, and pose its measurement as an open problem.
