arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.09652cs.CL

中文语言模型到底有多中国？中国LLM中令人困惑的语言政策缺失

How Chinese are Chinese Language Models? The Puzzling Lack of Language Policy in China's LLMs

Andrea W Wen-Yi, Unso Eun Seo Jo, Lu Jia Lin, David Mimno

备注：
We have reworked the paper substantially. Please refer to the new, updated article: arXiv:2504.00289
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

评估中国公司预训练的六个开源多语言LLM发现，其在18种语言上的表现与国际模型无异，且技术报告和政策中均缺乏针对语言多样性的明确策略，揭示了语言模型中语言政策的缺失。

摘要：

当代语言模型日益多语言化，但中国LLM开发者必须在语言多样性复杂的政治和商业考量中寻找平衡。中国的语言政策旨在影响公共话语和治理多民族社会，自1949年以来已逐渐从多元化转向更同化的方式。我们探讨了这些影响对当前语言技术的作用。我们评估了由中国公司预训练的六个开源多语言LLM，涵盖18种语言，广泛跨越中文、亚洲和盎格鲁-欧洲语言。实验表明，中国LLM在多样化语言上的表现与国际LLM难以区分。同样，模型技术报告也显示，除英语和普通话外，对预训练数据的语言覆盖缺乏考量。通过审查中国AI政策、模型实验和技术报告，我们发现中国LLM发展中没有任何支持或反对语言多样性的一致政策迹象。这留下了一个令人困惑的事实：尽管中国既规范人们日常使用的语言，也规范语言模型开发，但它们似乎对语言模型中的语言没有任何政策。

英文摘要：

Contemporary language models are increasingly multilingual, but Chinese LLM developers must navigate complex political and business considerations of language diversity. Language policy in China aims at influencing the public discourse and governing a multi-ethnic society, and has gradually transitioned from a pluralist to a more assimilationist approach since 1949. We explore the impact of these influences on current language technology. We evaluate six open-source multilingual LLMs pre-trained by Chinese companies on 18 languages, spanning a wide range of Chinese, Asian, and Anglo-European languages. Our experiments show Chinese LLMs performance on diverse languages is indistinguishable from international LLMs. Similarly, the models' technical reports also show lack of consideration for pretraining data language coverage except for English and Mandarin Chinese. Examining Chinese AI policy, model experiments, and technical reports, we find no sign of any consistent policy, either for or against, language diversity in China's LLM development. This leaves a puzzling fact that while China regulates both the languages people use daily as well as language model development, they do not seem to have any policy on the languages in language models.

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。

↑