当意义不再字面化：探索跨语言和模态的隐喻意义
When Meaning Isn't Literal: Exploring Idiomatic Meaning Across Languages and Modalities
AI总结：
本文提出Mediom多语言多模态隐喻语料库及HIDE框架，通过系统性测试揭示语言模型在隐喻理解上的缺陷，并为下一代AI系统提供文化根基的隐喻理解方法。
摘要：
隐喻推理与隐喻和文化紧密相关，但当前语言模型在这一领域仍存在明显不足，其进展偏向于表层词汇和语义线索。例如，孟加拉语隐喻'angur fol tok'（'葡萄是酸的'）编码的是否定驱动的合理化，但简单模型却会抓住字面的狐狸与葡萄意象。为解决这一问题，我们提出了包含3533个印地语、孟加拉语和泰语隐喻的多语言多模态语料库Mediom，每个隐喻均配有标准解释、跨语言翻译和精确对齐的文本-图像表示。我们对Mediom进行了基准测试，揭示了大型语言模型和视觉-语言模型在隐喻理解上的系统性失败。为缓解这些差距，我们提出HIDE框架，通过错误反馈检索和目标诊断线索进行迭代推理优化。集体而言，Mediom和HIDE为文化根基、多模态隐喻理解的下一代AI系统建立了严谨的测试平台和方法论。
英文摘要：
Idiomatic reasoning, deeply intertwined with metaphor and culture, remains a blind spot for contemporary language models, whose progress skews toward surface-level lexical and semantic cues. For instance, the Bengali idiom \textit{\foreignlanguage{bengali}{\char"0986\char"0999\char"09CD\char"0997\char"09C1 \char"09B0 \char"09AB\char"09B2 \char"099F\char"0995}} (angur fol tok, ``grapes are sour''): it encodes denial-driven rationalization, yet naive models latch onto the literal fox-and-grape imagery. Addressing this oversight, we present ``Mediom,'' a multilingual, multimodal idiom corpus of 3,533 Hindi, Bengali, and Thai idioms, each paired with gold-standard explanations, cross-lingual translations, and carefully aligned text--image representations. We benchmark both large language models (textual reasoning) and vision-language models (figurative disambiguation) on Mediom, exposing systematic failures in metaphor comprehension. To mitigate these gaps, we propose ``HIDE,'' a Hinting-based Idiom Explanation framework that leverages error-feedback retrieval and targeted diagnostic cues for iterative reasoning refinement. Collectively, Mediom and HIDE establish a rigorous test bed and methodology for culturally grounded, multimodal idiom understanding embedded with reasoning hints in next-generation AI systems.
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。
