发现跨语言隐喻生成存在可复用的内部信号，能跨语言有效引导生成。
Cross-Lingual Steering for Figurative Language Generation
- 用激活控制法在一种语言中学习隐喻信号，再用于其他语言生成。
- 在六种语言、五类隐喻中，跨语言迁移效果稳定，德语最易响应。
- 多语言信号组合可超越本族语言原生信号，证明共享机制存在。
多语言大模型能生成隐喻语言，但其内部驱动机制是否仅限于特定语言仍不明确。本文通过激活控制法，从一种语言的隐喻与字面表达激活差异中提取方向，并应用于生成过程。在六种语言、五类隐喻及四种多语言大模型上验证：该方向在本语言内可稳定引导生成，尤其对隐喻和明喻效果最佳；更重要的是，跨语言迁移有效——在一种语言中学习的方向可提升另一种语言中的目标行为，其中德语最为敏感。进一步发现，由其他语言组合的信号甚至可匹配或超越目标语言自身原生方向，而移除共享成分后原生控制力下降。结果直接表明，隐喻生成存在可复用但依赖目标语言的跨语言信号。
原文摘要 · Abstract (English)
Multilingual large language models can generate figurative language, but whether the internal signals driving this behavior are language-specific or reusable across languages is unclear. Using activation steering as a probe, we estimate a direction for a figurative category from figurative--literal activation differences in one language and apply it during generation. Across five figurative categories, six languages, and four multilingual LLMs, these directions steer reliably within their own language, most robustly for metaphor and simile. More importantly, they transfer across languages: a direction learned in one increases the target behavior when applied to another, with German among the most receptive targets. Going further, directions assembled from other languages can match or even surpass a target language's own native direction, while removing this shared component weakens native steering. Together, these results provide direct evidence of a reusable but target-dependent cross-lingual signal for figurative generation.
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。