Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

Framing Political Bias in Multilingual LLMs Across Pakistani Languages

Domaine:

natural language processing

Type de record:

paper
Créateur:
NadDraNas
Hôte:avatar
Large Language Models (LLMs) increasingly shape public discourse, yet most evaluations of political and economic bias have focused on high-resource, Western languages and contexts. This leaves critical blind spots in low-resource, multilingual regions such as Pakistan, where linguistic identity is closely tied to political, religious, and regional ideologies. We present a systematic evaluation of political bias in 13 state-of-the-art LLMs across five Pakistani languages: Urdu, Punjabi, Sindhi, Pashto, and Balochi. Our framework integrates a culturally adapted Political Compass Test (PCT) with multi-level framing analysis, capturing both ideological stance (economic/social axes) and stylistic framing (content, tone, emphasis). Prompts are aligned with 11 socio-political themes specific to the Pakistani context. Results show that while LLMs predominantly reflect liberal-left orientations consistent with Western training data, they exhibit more authoritarian framing in regional languages, highlighting language-conditioned ideological modulation. We also identify consistent model-specific bias patterns across languages. These findings show the need for culturally grounded, multilingual bias auditing frameworks in global NLP. Preprint

Visit

arxiv.org

Tasks

text classification

Tags

Computation and LanguageArtificial Intelligence

Similaires

Teaching LLMs to Abstain across Languages via Multilingual FeedbackLeveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense RetrievalRethinking Multilingual Continual Pretraining: Data Mixing for Adapting LLMs Across Languages and ResourcesMultilingual jailbreaking of LLMs using low-resource languagesGender Bias in Natural Language Processing Across Human LanguagesToward Robust Multilingual Adaptation of LLMs for Low-Resource Languages

Teaching LLMs to Abstain across Languages via Multilingual Feedback

Multilingual LLMs often have knowledge disparities across languages, with larger gaps in under-resou

Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrieval

There has been limited success for dense retrieval models in multilingual retrieval, due to uneven a

Rethinking Multilingual Continual Pretraining: Data Mixing for Adapting LLMs Across Languages and Resources

Large Language Models (LLMs) exhibit significant disparities in performance across languages, primar

Multilingual jailbreaking of LLMs using low-resource languages

Large Language Models (LLMs) remain vulnerable to jailbreak attempts that circumvent safety guardrai

Gender Bias in Natural Language Processing Across Human Languages

Natural Language Processing (NLP) systems are at the heart of many critical automated decision-makin

Toward Robust Multilingual Adaptation of LLMs for Low-Resource Languages

Large language models (LLMs) continue to struggle with low-resource languages, primarily due to limi