1
Mitigating Cross-Lingual Cultural Inconsistencies in LLMs via Consensus-Driven Preference Optimisation
探索通过共识驱动的偏好优化，解决多语言大模型在用户身份明确时的跨语言文化不一致问题
arXiv:2605.12515v2 Announce Type: replace Abstract: Despite their impressive capabilities, multilingual large language models (MLLMs) frequently exhib…