In-Place Instruction Following in Diffusion Language Models
GRAFT, an IPP-oriented post-training framework combining constraint-aware SFT and preference optimization is proposed, an IPP-oriented post-training framework combining constraint-aware SFT and preference optimization that raises the average IIF score and preserves general generation ability.
Zheng Nie, Zhe-Rui Li, Jia-Ming Zhang et al.
· 0 citations