作者位次 #5/9ACL 2026Poster· Natural Language Processing
LL a DA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models
Fengqi Zhu · Rongzhen Wang · Shen Nie · Xiaolu Zhang · Chunwei Wu · JUN ZHOU · Yankai Lin · Ji-Rong Wen · Chongxuan Li
摘要
Masked diffusion language models present a promising paradigm for language modeling, yet the systematic theoretical analysis and comprehensive empirical validation of their alignment on general tasks remain relatively underexplored. In this paper, we identify the primary challenge for this proble...