# Analysing LLM Persona Generation and Fairness Interpretation in Polarised Geopolitical Contexts

arXiv: https://arxiv.org/abs/2603.22837 · HTML: https://mlsanity.com/paper/2603.22837/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 32 references that are in the map.
- First posted on arXiv 24 Mar 2026.

## Builds on (most cited first, 20 of 20)

- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Towards Automated Circuit Discovery for Mechanistic Interpretability](https://mlsanity.com/paper/2304.14997/) (2023)
- [Towards Best Practices of Activation Patching in Language Models: Metrics and Methods](https://mlsanity.com/paper/2309.16042/) (2023)
- [A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily](https://mlsanity.com/paper/2311.08268/) (2023)
- [Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives](https://mlsanity.com/paper/2312.11970/) (2023)
- [Having Beer after Prayer? Measuring Cultural Bias in Large Language Models](https://mlsanity.com/paper/2305.14456/) (2023)
- [Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking](https://mlsanity.com/paper/2311.09827/) (2023)
- [This Land is {Your, My} Land: Evaluating Geopolitical Biases in Language Models](https://mlsanity.com/paper/2305.14610/) (2023)
- [Social Bias Probing: Fairness Benchmarking for Language Models](https://mlsanity.com/paper/2311.09090/) (2023)
- [IndiBias: A Benchmark Dataset to Measure Social Biases in Language Models for Indian Context](https://mlsanity.com/paper/2403.20147/) (2024)
- [Representation Bending for Large Language Model Safety](https://mlsanity.com/paper/2504.01550/) (2025)
- [Political-LLM: Large Language Models in Political Science](https://mlsanity.com/paper/2412.06864/) (2024)
- [GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models](https://mlsanity.com/paper/2406.13925/) (2024)
- [Large Language Models Still Exhibit Bias in Long Text](https://mlsanity.com/paper/2410.17519/) (2024)
- [Gender Bias in Decision-Making with Large Language Models: A Study of Relationship Conflicts](https://mlsanity.com/paper/2410.11084/) (2024)
- [Interpretable Embeddings with Sparse Autoencoders: A Data Analysis Toolkit](https://mlsanity.com/paper/2512.10092/) (2025)
- [How User Language Affects Conflict Fatality Estimates in ChatGPT](https://mlsanity.com/paper/2308.00072/) (2023)

## 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.