# Bias Beyond Borders: Political Ideology Evaluation and Steering in Multilingual LLMs

arXiv: https://arxiv.org/abs/2601.23001 · HTML: https://mlsanity.com/paper/2601.23001/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 40 references that are in the map.
- First posted on arXiv 30 Jan 2026.

## Builds on (most cited first, 19 of 19)

- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs](https://mlsanity.com/paper/2311.04892/) (2023)
- [The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientation](https://mlsanity.com/paper/2301.01768/) (2023)
- [Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do](https://mlsanity.com/paper/2103.11790/) (2021)
- ["I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Dataset](https://mlsanity.com/paper/2205.09209/) (2022)
- [Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models](https://mlsanity.com/paper/2402.16786/) (2024)
- [Mitigating Label Biases for In-context Learning](https://mlsanity.com/paper/2305.19148/) (2023)
- [Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey](https://mlsanity.com/paper/2210.07700/) (2022)
- [Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors](https://mlsanity.com/paper/2410.12299/) (2024)
- [Language Model Alignment in Multilingual Trolley Problems](https://mlsanity.com/paper/2407.02273/) (2024)
- [Assessing Political Prudence of Open-domain Chatbots](https://mlsanity.com/paper/2106.06157/) (2021)
- [Fairness and Bias in Multimodal AI: A Survey](https://mlsanity.com/paper/2406.19097/) (2024)
- [First-Person Fairness in Chatbots](https://mlsanity.com/paper/2410.19803/) (2024)
- [Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs](https://mlsanity.com/paper/2503.05371/) (2025)
- [Bias Vector: Mitigating Biases in Language Models with Task Arithmetic Approach](https://mlsanity.com/paper/2412.11679/) (2024)
- [Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models](https://mlsanity.com/paper/2502.15639/) (2025)
- [Steering Towards Fairness: Mitigating Political Bias in LLMs](https://mlsanity.com/paper/2508.08846/) (2025)
- [Framing Political Bias in Multilingual LLMs Across Pakistani Languages](https://mlsanity.com/paper/2506.00068/) (2025)
- [Fairness Evaluation and Inference Level Mitigation in LLMs](https://mlsanity.com/paper/2510.18914/) (2025)

## Built on by (most cited first, 4 of 4)

- [Collective Alignment in LLM Multi-Agent Systems: Disentangling Bias from Cooperation via Statistical Physics](https://mlsanity.com/paper/2605.10528/) (2026)
- [People Are Not Just Their Countries. Disentangling Social Determinants of LLM Value Alignment Across Europe](https://mlsanity.com/paper/2608.07367/) (2026)
- [Progressive in Principle, Centrist in Practice: LLM Political Bias Is Instrument-Dependent](https://mlsanity.com/paper/2606.00048/) (2026)
- [Validating LLMs in social science: Epistemic threats and emerging norms](https://mlsanity.com/paper/2607.07915/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) increasingly shape global discourse, making fairness and ideological neutrality essential for responsible AI deployment. Despite growing attention to political bias in LLMs, prior work largely focuses on high-resource, Western languages or narrow multilingual settings, leaving cross-lingual consistency and safe post-hoc mitigation underexplored. To address this gap, we present a large-scale multilingual evaluation of political bias spanning 50 countries and 33 languages. We introduce a complementary post-hoc mitigation framework, Cross-Lingual Alignment Steering (CLAS), designed to augment existing steering methods by aligning ideological representations across languages and dynamically regulating intervention strength. This method aligns latent ideological representations induced by political prompts into a shared ideological subspace, ensuring cross lingual consistency, with the adaptive mechanism prevents over correction and preserves coherence. Experiments demonstrate substantial bias reduction along both economic and social axes with minimal degradation in response quality. The proposed framework establishes a scalable and interpretable paradigm for fairness-aware multilingual LLM governance, balancing ideological neutrality with linguistic and cultural diversity.