Post-Training Language Models for Crosslingual Consistency 事件

Post-Training Language Models for Crosslingual Consistency arXiv:2603.04678v3 Announce Type: replace Abstract: Language models often respond inconsistently to translation-equivalent prompts across languages, undermining the reliability of multilingual systems. To quantify this, we give an information-theoretic definition of crosslingual consistency as a divergence bound between a model's response distribution and its round-trip pushforward across languages. We then introduce penalized consisten