Do Role-Playing Agents Practice What They Preach? Belief-Behavior Consistency in LLM-Based Simulations of Human Trust

TL;DR

This paper evaluates how well LLM-based role-playing agents' expressed beliefs align with their actual simulated behaviors in trust-related scenarios, revealing systematic inconsistencies that impact their use in behavioral research.

Contribution

The study introduces a framework and metric to measure belief-behavior consistency in LLM role-playing agents, highlighting factors influencing their coherence and implications for research use.

Findings

LLMs often show inconsistencies between stated beliefs and actions.

Beliefs about outcomes are less predictive of behavior than task-relevant attributes.

Imposing researcher priors can help align beliefs and behaviors.

Abstract

As LLMs are increasingly studied as role-playing agents to generate synthetic data for human behavioral research, ensuring that their outputs remain coherent with their assigned roles has become a critical concern. In this paper, we investigate how consistently LLM-based role-playing agents' stated beliefs about the behavior of the people they are asked to role-play ("what they say") correspond to their actual behavior during role-play ("how they act"). Specifically, we establish an evaluation framework to rigorously measure how well beliefs obtained by prompting the model can predict simulation outcomes in advance. Using an augmented version of the GenAgents persona bank and the Trust Game (a standard economic game used to quantify players' trust and reciprocity), we introduce a belief-behavior consistency metric to systematically investigate how it is affected by factors such as: (1) the types of beliefs we elicit from LLMs, like expected outcomes of simulations versus task-relevant attributes of individual characters LLMs are asked to simulate; (2) when and how we present LLMs with relevant information about Trust Game; and (3) how far into the future we ask the model to forecast its actions. We also explore how feasible it is to impose a researcher's own theoretical priors in the event that the originally elicited beliefs are misaligned with research objectives. Our results reveal systematic inconsistencies between LLMs' stated (or imposed) beliefs and the outcomes of their role-playing simulation, at both an individual- and population-level. Specifically, we find that, even when models appear to encode plausible beliefs, they may fail to apply them in a consistent way. These findings highlight the need to identify how and when LLMs' stated beliefs align with their simulated behavior, allowing researchers to use LLM-based agents appropriately in behavioral studies.