作者位次 #3/9ACL 2026Poster· Natural Language Processing
LEDOM : Reverse Language Model
Xunjian Yin · Sitao Cheng · Yuxi Xie · Xinyu Hu · Li Lin · Xinyi Wang · Liangming Pan · William Yang Wang · Xiaojun Wan
摘要
Autoregressive language models are trained exclusively left-to-right. We explore the complementary factorization, training right-to-left at scale, and ask what reasoning patterns emerge when a model conditions on future context to predict the past.We train LEDOM, an open-source purely reverse aut...