聊天机器人假设了哪些制度框架？审计多语言大语言模型中的司法默认值
Which Institutional Frameworks Do Chatbots Assume? Auditing Jurisdictional Defaults in Multilingual LLMs
AI总结：
研究多语言大语言模型在未指定司法管辖区时，是否将输入语言作为默认司法信号，通过审计7个模型在60个提示上的2520个响应，发现中文输入更常产生中国特定答案，英文输入更常产生美国特定答案，揭示了制度框架误选风险。
摘要：
大语言模型越来越多地回答有关税收、劳动保护、医疗保健、教育、养老金和行政程序的问题，其有用性通常取决于适用的司法管辖区。多语言用户可能使用他们最熟悉的语言书写，而不是与适用规则的国家或地区相关的语言。我们询问，当提示省略任何国家或地区时，部署的大语言模型是否将输入语言作为默认司法信号。先前的多语言审计表明，提示语言可以改变文化、政治或规范性输出；我们检查当司法管辖区未明确指定时，模型提供了哪种法律-行政框架。我们评估了在美国或中国开发的七个大语言模型，在英语和普通话的60个未明确指定司法管辖区的法律-行政提示下，在三种系统提示条件下，产生了2520个手动注释的响应。跨模型和条件，中文输入更常产生中国特定的答案，而英文输入更常产生美国特定、比较性或通用答案。需要单一答案的提示进一步增加了司法管辖区选择：跨模型汇总，74.5%的英文输入响应采用美国框架，而53.3%的中文输入响应采用中国框架。这种方向性模式出现在所有七个模型中。我们将这种部署层面的模式描述为制度框架误选风险：一个流畅的答案可能依赖于用户未意图的法律-行政背景，特别是当他们的首选语言与相关司法管辖区不同时。大语言模型界面不应仅通过输入语言来路由制度建议；当位置信息缺失时，应请求位置或说明答案的司法管辖区范围。
英文摘要：
LLMs increasingly answer questions about taxes, labor protections, healthcare, education, pensions, and administrative procedures, where usefulness often depends on the applicable jurisdiction. Multilingual users may write in their most comfortable language rather than one associated with the country or region whose rules apply. We ask whether deployed LLMs use input language as a default jurisdictional signal when prompts omit any country or region. Prior multilingual audits show that prompt language can shift cultural, political, or normative outputs; we examine which legal-administrative framework models supply when jurisdiction is underspecified. We evaluate seven LLMs developed in the United States or China on 60 underspecified legal-administrative prompts in English and Mandarin Chinese under three system-prompt conditions, yielding 2,520 manually annotated responses. Across models and conditions, Chinese input more often produces China-specific answers, while English input more often produces U.S.-specific, comparative, or generic answers. Prompts requiring a single answer further increase jurisdiction selection: pooled across models, 74.5% of English-input responses adopt a U.S. framework, while 53.3% of Chinese-input responses adopt a China framework. This directional pattern appears in all seven models. We describe this deployment-level pattern as institutional-framework misselection risk: a fluent answer may rely on a legal-administrative context the user did not intend, especially when their preferred language differs from the relevant jurisdiction. LLM interfaces should not route institutional advice by input language alone; when location is absent, they should request it or state the jurisdictional scope of the answer.
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。
