arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2604.04732cs.CLcs.AI

我们通过什么来计算隐喻:对文化翻译与LLM中思维的计算审计

Metaphors We Compute By: A Computational Audit of Cultural Translation vs. Thinking in LLMs

Yuan Chang, Jiaming Qu, Zhu Li

AI总结:

本文通过创造性写作任务研究LLM的文化包容性,发现模型在特定文化情境下存在刻板隐喻使用和西方默认倾向,表明单纯提示文化身份无法保证文化思维。

摘要:

大型语言模型(LLMs)常被描述为多语言,因为它们能理解和回应多种语言。然而,说一种语言并不等同于在文化中进行推理。这一区别促使一个关键问题:LLMs是否真正进行文化意识推理?本文对文化包容性进行了初步计算审计。我们实证检验LLMs是作为文化多样性的创造性伙伴,还是仅作为利用主导概念框架并带有本地表达的文化翻译者。通过涵盖五个文化情境和多个抽象概念的隐喻生成任务案例研究,我们发现模型在某些情境下表现出刻板的隐喻使用,以及西方默认倾向。这些发现表明,仅提示LLM具有文化身份并不保证文化基础的推理。

英文摘要:

Large language models (LLMs) are often described as multilingual because they can understand and respond in many languages. However, speaking a language is not the same as reasoning within a culture. This distinction motivates a critical question: do LLMs truly conduct culture-aware reasoning? This paper presents a preliminary computational audit of cultural inclusivity in a creative writing task. We empirically examine whether LLMs act as culturally diverse creative partners or merely as cultural translators that leverage a dominant conceptual framework with localized expressions. Using a metaphor generation task spanning five cultural settings and several abstract concepts as a case study, we find that the model exhibits stereotyped metaphor usage for certain settings, as well as Western defaultism. These findings suggest that merely prompting an LLM with a cultural identity does not guarantee culturally grounded reasoning.

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。

↑