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

• URL: http://arxiv.org/abs/2601.23001v2
• Date: Mon, 02 Feb 2026 05:40:17 GMT
• Title: Bias Beyond Borders: Political Ideology Evaluation and Steering in Multilingual LLMs
• Authors: Afrozah Nadeem, Agrima, Mehwish Nasim, Usman Naseem,
• Abstract summary: We present a large-scale multilingual evaluation of political bias spanning 50 countries and 33 languages.<n>We introduce a complementary post-hoc mitigation framework, Cross-Lingual Alignment Steering (CLAS), designed to augment existing steering methods.<n>Experiments demonstrate substantial bias reduction along both economic and social axes with minimal degradation in response quality.
• Score: 12.34382066368117
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Culturally-Grounded Governance for Multilingual Language Models: Rights, Data Boundaries, and Accountable AI Design [2.5424331328233207]
  This paper synthesizes existing evidence on multilingual model behavior, data asymmetries, and sociotechnical harm.<n>We identify three interrelated governance challenges: cultural and linguistic inequities in training data and evaluation practices, misalignment between global deployment and locally situated norms, values, and power structures, and limited accountability mechanisms for addressing harms experienced by marginalized language communities.<n>We argue that culturally grounded governance is essential for ensuring that multilingual language models do not reproduce existing global inequalities under the guise of scale and neutrality.
  arXiv  Detail & Related papers  (2026-01-31T03:47:30Z)
• When Meanings Meet: Investigating the Emergence and Quality of Shared Concept Spaces during Multilingual Language Model Training [57.230355403478995]
  We investigate the development of language-agnostic concept spaces during pretraining of EuroLLM.<n>We find that shared concept spaces emerge early and continue to refine, but that alignment with them is language-dependent.<n>In contrast to prior work, our fine-grained manual analysis reveals that some apparent gains in translation quality reflect shifts in behavior.
  arXiv  Detail & Related papers  (2026-01-30T11:23:01Z)
• When Abundance Conceals Weakness: Knowledge Conflict in Multilingual Models [18.969784662298174]
  Large Language Models encode vast world knowledge across multiple languages, yet their internal beliefs are often unevenly distributed across linguistic spaces.<n> CLEAR decomposes conflict resolution into four progressive scenarios, from multilingual parametric elicitation to competitive multi-source induction.<n>In reasoning-intensive tasks, conflict resolution is dominated by language resource abundance, with high-resource languages exerting stronger persuasive power.
  arXiv  Detail & Related papers  (2026-01-11T19:26:59Z)
• Latent Topic Synthesis: Leveraging LLMs for Electoral Ad Analysis [51.95395936342771]
  We introduce an end-to-end framework for automatically generating an interpretable topic taxonomy from an unlabeled corpus.<n>We apply this framework to a large corpus of Meta political ads from the month ahead of the 2024 U.S. Presidential election.<n>Our approach uncovers latent discourse structures, synthesizes semantically rich topic labels, and annotates topics with moral framing dimensions.
  arXiv  Detail & Related papers  (2025-10-16T20:30:20Z)
• On the Entity-Level Alignment in Crosslingual Consistency [62.33186691736433]
  SubSub and SubInj integrate English translations of subjects into prompts across languages, leading to substantial gains in factual recall accuracy and consistency.<n>These interventions reinforce the entity representation alignment in the conceptual space through model's internal pivot-language processing.
  arXiv  Detail & Related papers  (2025-10-11T16:26:50Z)
• Code-Switching In-Context Learning for Cross-Lingual Transfer of Large Language Models [64.54005959758733]
  We introduce code-switching in-context learning (CSICL) as a principled and robust approach for overcoming the translation barrier during inference.<n>We conduct extensive experiments across 4 LLMs, 6 datasets, and 10 languages, spanning both knowledge-intensive and reasoning-oriented domains.<n>Our results demonstrate CSICL consistently outperforms X-ICL baselines, achieving gains of 3.1%p and 1.9%p in both target and unseen languages.
  arXiv  Detail & Related papers  (2025-10-07T08:35:42Z)
• Framing Political Bias in Multilingual LLMs Across Pakistani Languages [6.5137518437747]
  We present a systematic evaluation of political bias in 13 state-of-the-art Large Language Models (LLMs) across five Pakistani languages.<n>Our framework integrates a culturally adapted Political Compass Test (PCT) with multi-level framing analysis.<n>Results show that while LLMs predominantly reflect liberal-left orientations consistent with Western training data, they exhibit more authoritarian framing in regional languages.
  arXiv  Detail & Related papers  (2025-05-29T15:15:42Z)
• Probing the Subtle Ideological Manipulation of Large Language Models [0.3745329282477067]
  Large Language Models (LLMs) have transformed natural language processing, but concerns have emerged about their susceptibility to ideological manipulation.<n>We introduce a novel multi-task dataset designed to reflect diverse ideological positions through tasks such as ideological QA, statement ranking, manifesto cloze completion, and Congress bill comprehension.<n>Our findings indicate that fine-tuning significantly enhances nuanced ideological alignment, while explicit prompts provide only minor refinements.
  arXiv  Detail & Related papers  (2025-04-19T13:11:50Z)
• The Hidden Space of Safety: Understanding Preference-Tuned LLMs in Multilingual context [0.9130277390156759]
  Alignment tuning has enabled large language models to excel in reasoning, instruction-following, and minimizing harmful generations.<n>Despite their widespread deployment, these models exhibit a monolingual bias, raising concerns about the effectiveness of alignment across languages.<n>Current alignment methods predominantly focus on English, leaving it unclear how alignment mechanism generalizes to multilingual settings.
  arXiv  Detail & Related papers  (2025-04-03T15:46:46Z)
• High-Dimensional Interlingual Representations of Large Language Models [65.77317753001954]
  Large language models (LLMs) trained on massive multilingual datasets hint at the formation of interlingual constructs.<n>We explore 31 diverse languages varying on their resource-levels, typologies, and geographical regions.<n>We find that multilingual LLMs exhibit inconsistent cross-lingual alignments.
  arXiv  Detail & Related papers  (2025-03-14T10:39:27Z)
• Cross-linguistic disagreement as a conflict of semantic alignment norms in multilingual AI~Linguistic Diversity as a Problem for Philosophy, Cognitive Science, and AI~ [0.2443066828522608]
  Cross-linguistic consistency (CL-consistency) seeks universal concepts across languages.<n>Folk-consistency, which respects language-specific semantic norms.<n>Findings challenge assumption that universal representations and cross-linguistic transfer capabilities are inherently desirable.
  arXiv  Detail & Related papers  (2025-03-01T03:31:40Z)
• Lens: Rethinking Multilingual Enhancement for Large Language Models [70.85065197789639]
  We propose Lens, a novel approach to enhance multilingual capabilities in large language models (LLMs)<n>Lens operates on two subspaces: the language-agnostic subspace, where it aligns target languages with the central language to inherit strong semantic representations, and the language-specific subspace, where it separates target and central languages to preserve linguistic specificity.<n>Lens significantly improves multilingual performance while maintaining the model's English proficiency, achieving better results with less computational cost compared to existing post-training approaches.
  arXiv  Detail & Related papers  (2024-10-06T08:51:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.