发表机构
Massachusetts Institute of Technology; Stanford University; University of California San Diego(麻省理工学院; 斯坦福大学; 加利福尼亚大学圣迭戈分校)
机构由 AI 辅助整理,请以论文原文为准。AI 中文总结
针对多语言模型目标语言生成问题,提出最优控制方法,在语言遵从性、连贯性上优于或持平均值差激活引导,且超参数调整更少。
AI 中文摘要
确保多语言语言模型在特定目标语言中生成连贯文本是多语言语言建模中的一个主要问题。我们开发了一种用于目标语言文本生成的最优控制方法,以及一个从语言遵从性、语言连贯性和语义连贯性方面评估生成文本质量的框架。我们发现,对于测试的大多数模型,所提出的方法在性能上至少与著名的均值差激活引导方法相当,且所需的超参数调整大幅减少。
英文摘要
Ensuring that multilingual language models generate coherent text in a specific target language is a major issue in multilingual language modeling. We develop an optimal control method for target-language text generation as well as a framework for evaluating the quality of generated text in terms of language adherence, linguistic coherence, and semantic coherence. We find that the proposed method performs at least as well as the prominent difference-in-means activation steering method for the majority of models tested, with substantially less hyperparameter tuning required.
CommentsAccepted at EMNLP 2026