mlsanityData to 7 Oct 2026

Large Language Models can Achieve Social Balance

arXiv 2410.04054 ↗First posted 5 Oct 2024cs.CL cs.AI cs.MAcited by 5

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) can be deployed in situations where they process positive/negative interactions with other agents. We study how this is done under the sociological framework of social balance, which explains the emergence of one faction or multiple antagonistic ones among agents. Across different LLM models, we find that balance depends on the (i) type of interaction, (ii) update mechanism, and (iii) population size. Across (i)-(iii), we characterize the frequency at which social balance is achieved, the justifications for the social dynamics, and the diversity and stability of interactions. Finally, we explain how our findings inform the deployment of agentic systems.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 38 of its 68 references that are in the map. First posted on arXiv 5 Oct 2024.

Builds on

38 of 68 references.

References · 38

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  5. 2017Deep reinforcement learning from human preferencescited by 3,846
  6. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  7. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  8. 2022Emergent Abilities of Large Language Modelscited by 2,483
  9. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  10. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 888
  11. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 752
  12. 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 506
26 more
  1. 2023SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agentscited by 350
  2. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectivescited by 253
  3. 2023InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviewscited by 177
  4. 2023Personality Traits in Large Language Modelscited by 166
  5. 2023In-Context Impersonation Reveals Large Language Models' Strengths and Biasescited by 154
  6. 2023EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activitiescited by 154
  7. 2023Simulating Opinion Dynamics with Networks of LLM-based Agentscited by 153
  8. 2023Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Dutiescited by 97
  9. 2018Community Interaction and Conflict on the Webcited by 72
  10. 2023Can ChatGPT Assess Human Personalities? A General Evaluation Frameworkcited by 69
  11. 2023CompeteAI: Understanding the Competition Dynamics in Large Language Model-based Agentscited by 65
  12. 2023GPT-RE: In-context Learning for Relation Extraction using Large Language Modelscited by 62
  13. 2021SDGNN: Learning Node Representation for Signed Directed Networkscited by 44
  14. 2023How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilitiescited by 33
  15. 2023The Wisdom of Partisan Crowds: Comparing Collective Intelligence in Humans and LLM-based Agentscited by 30
  16. 2015A Survey of Signed Network Mining in Social Mediacited by 25
  17. 2024What Does the Bot Say? Opportunities and Risks of Large Language Models in Social Media Bot Detectioncited by 24
  18. 2021POLE: Polarized Embedding for Signed Networkscited by 16
  19. 2020The Four Dimensions of Social Network Analysis: An Overview of Research Methods, Applications, and Software Toolscited by 9
  20. 2017Dynamics over Signed Networkscited by 8
  21. 2024On the Principles behind Opinion Dynamics in Multi-Agent Systems of Large Language Modelscited by 8
  22. 2017Dynamic Social Balance and Convergent Appraisals via Homophily and Influence Mechanismscited by 1
  23. 2019Polarization and Fluctuations in Signed Social Networkscited by 1
  24. 2019Signed Network Formation Games and Clustering Balancecited by 1
  25. 2019Structural Balance via Gradient Flows over Signed Graphscited by 1
  26. 2020The 1995-2018 Global Evolution of the Network of Amicable and Hostile Relations Among Nation-Statescited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 3.

5 papers.

  1. 2025The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societiescited by 12
  2. 2025Bypassing Safety Guardrails in LLMs Using Humorcited by 1
  3. 2026When Is Emergent Consensus Real? A Measured Coupling Gain and a Validity Diagnostic for LLM Agent Societiescited by 1
  4. 2026Can One-sided Arguments Lead to Response Change in Large Language Models?cited by 0
  5. 2026Who Does What? Archetypes of Roles Assigned to LLMs During Human-AI Decision-Makingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Population Physics, Population Problems: Safety and Emergence in LLM Societies
  2. 2026Benchmarking large language model agent societies against human behavioural distributions
  3. 2026Collective cooperation without individual fidelity in LLM agents
  4. 2024Static network structure cannot stabilize cooperation among Large Language Model agents
  5. 2026Collective Opinion Dynamics in Structured LLM Populations
  6. 2025Group size effects and collective misalignment in LLM multi-agent systems
  7. 2026An Empirical Study of Collective Behaviors and Social Dynamics in Large Language Model Agents
  8. 2025Large Language Models Miss the Multi-Agent Mark