A training objective that keeps prompts clean and applies diffusion only to the continuation improves diffusion language models on continuation benchmarks without changing inference.
Jason Lee, Elman Mansimov, and Kyunghyun Cho
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Reducing Pretraining-Generation Mismatch in Diffusion Language Models
A training objective that keeps prompts clean and applies diffusion only to the continuation improves diffusion language models on continuation benchmarks without changing inference.