作者位次 #3/9ACL 2026Poster· Natural Language Processing
Location Not Found: Exposing Implicit Local and Global Biases in Multilingual LLM s
Guy Mor-Lan · Omer Goldman · Matan Eyal · Adi Mayrav Gilady · Sivan Eiger · Idan Szpektor · Avinatan Hassidim · Yossi Matias · Reut Tsarfaty
摘要
Multilingual large language models (LLMs) have minimized the fluency gap between languages. This advancement, however, exposes models to the risk of biased behavior, as knowledge and norms may propagate across languages. In this work we aim to quantify models’ inter- and intra-lingual biases, via...