评测13个大模型在5种巴基斯坦语言中的政治偏见，发现区域性语言下更倾向威权立场。
Framing Political Bias in Multilingual LLMs Across Pakistani Languages
- 用本土化政治光谱测试+多层语义分析框架评估偏见
- 多数模型在地区语言中呈现威权倾向，非西方训练数据影响显著
- 揭示模型特有偏见模式，适合关注多元文化AI公平性的研究者
大型语言模型日益影响公共话语，但现有政治与经济偏见评估主要集中于高资源、西方语言和语境，忽视了巴基斯坦等低资源多语言地区。本文系统评估了13个前沿LLM在乌尔都语、旁遮普语、信德语、普什图语和俾路支语五种巴基斯坦语言中的政治偏见。框架融合本土化政治光谱测试（PCT）与多层次语义分析，捕捉意识形态立场（经济/社会轴）与表达风格（内容、语气、强调）。提示语基于11个巴基斯坦特定社会政治主题设计。结果显示，尽管模型总体反映与西方训练数据一致的自由左翼倾向，但在区域语言中表现出更强的威权式表述，凸显语言相关的意识形态调制。还发现跨语言存在的模型特异性偏见模式。研究强调需建立植根文化的多语言偏见审计体系。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。