# Mind the (Belief) Gap: Group Identity in the World of LLMs

arXiv: https://arxiv.org/abs/2503.02016 · HTML: https://mlsanity.com/paper/2503.02016/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 54 references that are in the map.
- First posted on arXiv 3 Mar 2025.

## Builds on (most cited first, 10 of 10)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://mlsanity.com/paper/2310.11667/) (2023)
- ["Liar, Liar Pants on Fire": A New Benchmark Dataset for Fake News Detection](https://mlsanity.com/paper/1705.00648/) (2017)
- [Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions](https://mlsanity.com/paper/2410.02584/) (2024)
- [Social Media Polarization and Echo Chambers in the Context of COVID-19: Case Study](https://mlsanity.com/paper/2103.10979/) (2021)
- [Polarization of Autonomous Generative AI Agents Under Echo Chambers](https://mlsanity.com/paper/2402.12212/) (2024)
- [Analyzing the Impact of Fake News on the Anticipated Outcome of the 2024 Election Ahead of Time](https://mlsanity.com/paper/2312.03750/) (2023)

## Built on by (most cited first, 12 of 12)

- [The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societies](https://mlsanity.com/paper/2509.18052/) (2025)
- [BeliefShift: Benchmarking Temporal Belief Consistency and Opinion Drift in LLM Agents](https://mlsanity.com/paper/2603.23848/) (2026)
- [The Lock-in Hypothesis: Stagnation by Algorithm](https://mlsanity.com/paper/2506.06166/) (2025)
- [Many LLMs Are More Utilitarian Than One](https://mlsanity.com/paper/2507.00814/) (2025)
- [A Review of Incorporating Psychological Theories in LLMs](https://mlsanity.com/paper/2505.00003/) (2025)
- [The Social Cost of Intelligence: Emergence, Propagation, and Amplification of Stereotypical Bias in Multi-Agent Systems](https://mlsanity.com/paper/2510.10943/) (2025)
- [Free Lunch for User Experience: Crowdsourcing Agents for Scalable User Studies](https://mlsanity.com/paper/2505.22981/) (2025)
- [Belief-Sim: Towards Belief-Driven Simulation of Demographic Misinformation Susceptibility](https://mlsanity.com/paper/2603.03585/) (2026)
- [The Curious Case of Curiosity across Human Cultures and LLMs](https://mlsanity.com/paper/2510.12943/) (2025)
- [LLM-enabled Social Agents](https://mlsanity.com/paper/2605.02335/) (2026)
- [Whose Norms? Disentangling Cultural and Personal Alignment in Large Language Models](https://mlsanity.com/paper/2606.07877/) (2026)
- [Do LLMs Take Care of Their Own? Similarity Signals Can Induce Cooperation](https://mlsanity.com/paper/2608.12125/) (2026)

## Abstract (arXiv)

Social biases and belief-driven behaviors can significantly impact Large Language Models (LLMs) decisions on several tasks. As LLMs are increasingly used in multi-agent systems for societal simulations, their ability to model fundamental group psychological characteristics remains critical yet under-explored. In this study, we present a multi-agent framework that simulates belief congruence, a classical group psychology theory that plays a crucial role in shaping societal interactions and preferences. Our findings reveal that LLMs exhibit amplified belief congruence compared to humans, across diverse contexts. We further investigate the implications of this behavior on two downstream tasks: (1) misinformation dissemination and (2) LLM learning, finding that belief congruence in LLMs increases misinformation dissemination and impedes learning. To mitigate these negative impacts, we propose strategies inspired by: (1) contact hypothesis, (2) accuracy nudges, and (3) global citizenship framework. Our results show that the best strategies reduce misinformation dissemination by up to 37% and enhance learning by 11%. Bridging social psychology and AI, our work provides insights to navigate real-world interactions using LLMs while addressing belief-driven biases.