language-fairness

该论文测量了2026年主流LLM分词器对法语及法国地方语言的token溢价（法语比英语多31%–58%，地方语言高达1.6–3.3倍），并提出法语优化的字节级BPE原型Baracoda FR v1.2，在法语上比Tekken少用11.5%的token。

This paper introduces LingT2I, a 10-language, 33K-prompt benchmark for evaluating cross-lingual consistency in text-to-image generation, revealing linguistic inequality and language-dependent trade-offs across content generation and text rendering.