Diffusion Language Models Generation Can Be Halted Early

Anonymous

TL;DR: Early Exiting methods for Diffusion Language Models

Abstract: Diffusion Language models (DLMs) are a promising avenue for text generation due to their practical properties on tractable controllable generation. They also have the advantage of not having to predict text autoregressively. However, despite these notable features, DLMs have not yet reached the performance levels of their Autoregressive counterparts. One of the ways to reduce the performance gap between these two types of language models is to speed up the generation of DLMs. Therefore, we propose a pioneering methodology to address this issue in this work. It enables the execution of more generation steps within a given time frame, potentially leading to higher-quality outputs. Specifically, our methods estimate DLMs completeness of text generation and allow adaptive halting of the generation process. We test and refine our methods on Plaid, SSD, and CDCD DLMs and create a cohesive perspective on their generation workflows. Finally, we confirm that our methods allow halting Plaid, SSD, and CDCD models and decrease the generation time by $10$-$40$% without a drop in the quality of model samples.

Paper Type: long

Research Area: Generation

Contribution Types: Model analysis & interpretability, Approaches low compute settings-efficiency, Publicly available software and/or pre-trained models

Languages Studied: English