Language Rectified Flow: Advancing Diffusion Language Generation with Probabilistic Flows

arXiv:2403.16995v1 Announce Type: cross
Abstract: Recent works have demonstrated success in controlling sentence attributes ($e.g.$, sentiment) and structure ($e.g.$, syntactic structure) based on the diffusion language model. A key component that drives theimpressive performance for generating high-quality samples from noise is iteratively denoise for thousands of steps. While beneficial, the complexity of starting from the noise and the learning steps has limited its implementation to many NLP real-world applications. This paper proposes Language Rectified Flow ({\ours}). Our method is based …

abstract arxiv cs.ai cs.cl cs.lg diffusion flow key language language generation language model noise performance quality samples sentiment stat.ml success type