流畅但异域：即使区域LLM也缺乏文化契合
Fluent but Foreign: Even Regional LLMs Lack Cultural Alignment
AI总结：
研究发现，即使区域LLM也缺乏文化契合，需通过社区基础的数据和厚宽评估来构建真正主权的LLM。
摘要：
大型语言模型（LLMs）被全球广泛使用，但表现出西方文化倾向。许多国家现在正在构建“区域”或“主权”LLM，但尚不清楚它们是否反映了本地的价值和实践，还是仅仅使用本地语言。以印度为例，我们基于全国代表性调查和社区来源的问答数据集，评估了六个印度语和六个全球LLM在两个维度——价值观和实践上的表现。在各项任务中，印度模型并不比全球模型更符合印度规范；事实上，美国受访者比任何印度模型更接近印度价值观。我们进一步对115名印度用户进行了用户研究，发现来自全球和印度语LLM的写作建议会引入西方化或异域化的写作。提示和区域微调未能恢复契合，甚至可能降低现有知识。我们将其归因于文化基础数据稀缺，尤其是预训练阶段。我们将文化评估定位为多语言基准的同等要求，并提供了一种可重用的、社区基础的方法。我们呼吁原生、社区编写的语料库和厚宽评估，以构建真正主权的LLM。
英文摘要：
Large language models (LLMs) are used worldwide, yet exhibit Western cultural tendencies. Many countries are now building ``regional'' or ``sovereign'' LLMs, but it remains unclear whether they reflect local values and practices or merely speak local languages. Using India as a case study, we evaluate six Indic and six global LLMs on two dimensions -- values and practices -- grounded in nationally representative surveys and community-sourced QA datasets. Across tasks, Indic models do not align better with Indian norms than global models; in fact, a U.S. respondent is a closer proxy for Indian values than any Indic model. We further run a user study with 115 Indian users and find that writing suggestions from both global and Indic LLMs introduce Westernized or exoticized writing. Prompting and regional fine-tuning fail to recover alignment and can even degrade existing knowledge. We attribute this to scarce culturally grounded data, especially for pretraining. We position cultural evaluation as a first-class requirement alongside multilingual benchmarks and offer a reusable, community-grounded methodology. We call for native, community-authored corpora and thickxwide evaluations to build truly sovereign LLMs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
