mlsanityData to 7 Oct 2026

Analysing LLM Persona Generation and Fairness Interpretation in Polarised Geopolitical Contexts

arXiv 2603.22837 ↗First posted 24 Mar 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) are increasingly utilised for social simulation and persona generation, necessitating an understanding of how they represent geopolitical identities. In this paper, we analyse personas generated for Palestinian and Israeli identities by five popular LLMs across 640 experimental conditions, varying context (war vs non-war) and assigned roles. We observe significant distributional patterns in the generated attributes: Palestinian profiles in war contexts are frequently associated with lower socioeconomic status and survival-oriented roles, whereas Israeli profiles predominantly retain middle-class status and specialised professional attributes. When prompted with explicit instructions to avoid harmful assumptions, models exhibit diverse distributional changes, e.g., marked increases in non-binary gender inferences or a convergence toward generic occupational roles (e.g., "student"), while the underlying socioeconomic distinctions often remain. Furthermore, analysis of reasoning traces reveals an interesting dynamics between model reasoning and generation: while rationales consistently mention fairness-related concepts, the final generated personas follow the aforementioned diverse distributional changes. These findings illustrate a picture of how models interpret geopolitical contexts, while suggesting that they process fairness and adjust in varied ways; there is no consistent, direct translation of fairness concepts into representative outcomes.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 32 references that are in the map. First posted on arXiv 24 Mar 2026.

Builds on

20 of 32 references.

References · 20

  1. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  2. 2023Sparse Autoencoders Find Highly Interpretable Features in Language Modelscited by 1,359
  3. 2024Refusal in Language Models Is Mediated by a Single Directioncited by 960
  4. 2021Ethical and social risks of harm from Language Modelscited by 957
  5. 2023Towards Automated Circuit Discovery for Mechanistic Interpretabilitycited by 700
  6. 2023Towards Best Practices of Activation Patching in Language Models: Metrics and Methodscited by 328
  7. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectivescited by 253
  8. 2023A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easilycited by 242
  9. 2023Having Beer after Prayer? Measuring Cultural Bias in Large Language Modelscited by 153
  10. 2023Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinkingcited by 78
  11. 2024IndiBias: A Benchmark Dataset to Measure Social Biases in Language Models for Indian Contextcited by 32
  12. 2023This Land is {Your, My} Land: Evaluating Geopolitical Biases in Language Modelscited by 31
8 more
  1. 2023Social Bias Probing: Fairness Benchmarking for Language Modelscited by 29
  2. 2025Representation Bending for Large Language Model Safetycited by 28
  3. 2024Political-LLM: Large Language Models in Political Sciencecited by 27
  4. 2024GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Modelscited by 18
  5. 2024Large Language Models Still Exhibit Bias in Long Textcited by 16
  6. 2024Gender Bias in Decision-Making with Large Language Models: A Study of Relationship Conflictscited by 15
  7. 2025Interpretable Embeddings with Sparse Autoencoders: A Data Analysis Toolkitcited by 9
  8. 2023How User Language Affects Conflict Fatality Estimates in ChatGPTcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Political Bias in LLMs: Unaligned Moral Values in Agent-centric Simulations
  2. 2025Computational Basis of LLM's Decision Making in Social Simulation
  3. 2025German General Social Survey Personas: A Survey-Derived Persona Prompt Collection for Population-Aligned LLM Studies
  4. 2025Population-Aligned Persona Generation for LLM-based Social Simulation
  5. 2025Persona-Assigned Large Language Models Exhibit Human-Like Motivated Reasoning
  6. 2025Hedging and Non-Affirmation: Quantifying LLM Alignment on Questions of Human Rights
  7. 2026Culturally Grounded Personas in Large Language Models: Characterization and Alignment with Socio-Psychological Value Frameworks
  8. 2025Us-vs-Them bias in Large Language Models ↗