作者位次 #4/5ICML 2026Poster· Deep Learning / Large Language Models
Translation Heads: Disentangling meaning from language in LLM-based machine translation
Théo Lasnier · Armel Randy Zebaze · Djamé Seddah · Rachel Bawden · Benoît Sagot
多语言与语言学OpenReview
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Théo Lasnier · Armel Randy Zebaze · Djamé Seddah · Rachel Bawden · Benoît Sagot
Nathan Godey · Wissam Antoun · Rian Touchent · Rachel Bawden · Éric Villemonte de la Clergerie · Benoît Sagot · Djamé Seddah
Standardized benchmarks have become the dominant metric for measuring progress in large language models, yet their validity is increasingly compromised by data contamination and the unclear relationship between benchmark scores and genuine language understanding. We introduce Gaperon, a suite of...