大模型看似多语，实则偏科，真实表现远不如宣称的那么强。
Lost in the Tower of Babel: The Adverse Effects of Incidental Multilingualism in LLMs
- 用网页数据训练导致模型只是偶然会多语，非刻意设计。
- 测试发现模型自称支持的语言和实际能回应的语言严重不一致。
- 简单语言切换攻击就能暴露模型对语言的隐藏假设，适合做系统评估者看。
本文指出，当前多语言自然语言处理已陷入一种脆弱且误导性的‘偶然多语’范式：大模型看似多语，实则源于海量不均衡的网络语料训练，并非以多语言或跨文化能力为核心设计目标。这种范式导致模型在不同语言间表现不均、脆弱且行为不可预测，在需跨语言推理、规划与行动的真实场景中后果严重。我们开展了一项实证研究，聚焦两个问题：模型自述支持哪些语言，以及在多语言提示下实际能响应哪些语言。结果表明两者差异显著。此外，我们展示了一种简单的语言切换攻击即可暴露这些缺陷，并揭示模型背后隐含的语言假设。为此，我们呼吁转向‘以多语为设计核心’的研究范式，将公平多语表现、文化适配性与跨语言行为理解作为模型全链条的一等目标。
原文摘要 · Abstract (English)
This paper argues that contemporary multilingual NLP has converged on a fragile and misleading paradigm of incidental multilingualism. Today's LLMs appear multilingual largely because they are trained on massive, uneven web corpora, not because multilingual or multicultural competence has been treated as a core design objective. We contend that this paradigm systematically produces unequal, brittle, and opaque behavior across languages, with severe consequences in real-world and agentic deployments where models must reason, plan, and act across multiple linguistic contexts. We report a focused empirical study of two practical questions: which languages models self-report as supported and which languages they actually respond in across multilingual prompts. We additionally demonstrate how even a simple language-change attack can surface these failures and expose hidden assumptions about language in LLM-based systems. To address this, we call for a shift toward multilingualism by design: a research agenda that treats equitable multilingual performance, cultural grounding, and cross-lingual behavioral understanding as first-class goals in all aspects of the model pipeline.
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。