# From the Fluency Fallacy to the Micro-to-Macro Validity Gap: Opportunities and Pitfalls of LLMs in Social Simulation

arXiv: https://arxiv.org/abs/2507.19364 · HTML: https://mlsanity.com/paper/2507.19364/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 81 references that are in the map.
- First posted on arXiv 25 Jul 2025.

## Builds on (most cited first, 30 of 41)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting](https://mlsanity.com/paper/1901.09451/) (2019)
- [Humans or LLMs as the Judge? A Study on Judgement Biases](https://mlsanity.com/paper/2402.10669/) (2024)
- [Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks](https://mlsanity.com/paper/2302.08399/) (2023)
- [Small Language Models are the Future of Agentic AI](https://mlsanity.com/paper/2506.02153/) (2025)
- [Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives](https://mlsanity.com/paper/2312.11970/) (2023)
- [S3: Social-network Simulation System with Large Language Model-Empowered Agents](https://mlsanity.com/paper/2307.14984/) (2023)
- [AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society](https://mlsanity.com/paper/2502.08691/) (2025)
- [Simulating Opinion Dynamics with Networks of LLM-based Agents](https://mlsanity.com/paper/2311.09618/) (2023)
- [Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems](https://mlsanity.com/paper/2410.07283/) (2024)
- [Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia](https://mlsanity.com/paper/2312.03664/) (2023)
- [What Large Language Models Know and What People Think They Know](https://mlsanity.com/paper/2401.13835/) (2024)
- [Cognitive Bias in Decision-Making with LLMs](https://mlsanity.com/paper/2403.00811/) (2024)
- [LLM Social Simulations Are a Promising Research Method](https://mlsanity.com/paper/2504.02234/) (2025)
- [From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents](https://mlsanity.com/paper/2412.03563/) (2024)
- [Factuality of Large Language Models: A Survey](https://mlsanity.com/paper/2402.02420/) (2024)
- [Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMs](https://mlsanity.com/paper/2403.05020/) (2024)
- [GenSim: A General Social Simulation Platform with Large Language Model based Agents](https://mlsanity.com/paper/2410.04360/) (2024)
- [Understanding the Performance and Estimating the Cost of LLM Fine-Tuning](https://mlsanity.com/paper/2408.04693/) (2024)
- [Actions Speak Louder than Words: Agent Decisions Reveal Implicit Biases in Language Models](https://mlsanity.com/paper/2501.17420/) (2025)

## Built on by (most cited first, 10 of 10)

- [Understanding Agent Scaling in LLM-Based Multi-Agent Systems via Diversity](https://mlsanity.com/paper/2602.03794/) (2026)
- [Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces](https://mlsanity.com/paper/2604.08362/) (2026)
- [CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2604.12461/) (2026)
- [Modeling realistic human behavior using generative agents in a multimodal transport system: Software architecture and Application to Toulouse](https://mlsanity.com/paper/2510.19497/) (2025)
- [Is Lying an Emergent Behaviour in LLMs? Evidence from Gaslighting AI agents in a Sustainability Game](https://mlsanity.com/paper/2606.28456/) (2026)
- [Long-term Measurements: Towards a Longitudinal Understanding of Human-AI Interactions](https://mlsanity.com/paper/2608.02491/) (2026)
- [SocialFiVis: A Visual Analytics Sandbox for LLM-Grounded Multi-Agent Simulation in Social Finance](https://mlsanity.com/paper/2608.08497/) (2026)
- [Do Personality-Tuned LLMs Make Better Social Agents?](https://mlsanity.com/paper/2609.21857/) (2026)
- [Joint Workflow and Prompt Optimization for User Behavior Simulation](https://mlsanity.com/paper/2610.07663/) (2026)
- [The AI Evaluation Ecosystem](https://mlsanity.com/paper/2610.09296/) (2026)

## Abstract (arXiv)

The integration of Large Language Models (LLMs) into social simulation has generated enthusiasm but also raises methodological and epistemological challenges. This critical review examines LLMs as cognitive or decision-making components of simulated agents from a computational social science perspective. We argue that their behavioral and epistemic limitations can become systemic vulnerabilities when scaled to multi-agent societies. We map the evolving landscape of LLM-driven platforms, from narrative sandboxes to population-scale simulations, and develop a framework for analyzing the Micro-to-Macro Validity Gap: the propagation, amplification, or contraction of micro-level limitations-including hallucinations, stochastic inconsistency, representational biases, and alignment effects-into agent-level distortions (e.g., persona convergence) and macro-level risks (e.g., artificial consensus and behavioral homogenization). We also highlight evaluative vulnerabilities such as the Fluency Fallacy and automation bias. We identify contexts where LLM-based agents offer operational value, including serious games, participatory environments, and exploratory modeling, distinguishing these uses from confirmatory research with unconstrained models and precise social forecasting. Finally, we examine theory-driven hybrid architectures embedding LLMs in explicit, mechanistic, and reproducible Agent-Based Modeling (ABM) frameworks. While promising, these architectures do not guarantee epistemic control: validity requires multi-level evaluation of environmental dynamics, individual behavior, cross-level interactions, and aggregate outcomes. They also remain vulnerable to physics washing.