Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ye, Jiasheng, Zheng, Zaixiang, Bao, Yu, Qian, Lihua, Gu, Quanquan
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915168358760448
author Ye, Jiasheng
Zheng, Zaixiang
Bao, Yu
Qian, Lihua
Gu, Quanquan
author_facet Ye, Jiasheng
Zheng, Zaixiang
Bao, Yu
Qian, Lihua
Gu, Quanquan
contents The recent surge of generative AI has been fueled by the generative power of diffusion probabilistic models and the scalable capabilities of large language models. Despite their potential, it remains elusive whether diffusion language models can solve general language tasks comparable to their autoregressive counterparts. This paper demonstrates that scaling diffusion models w.r.t. data, sizes, and tasks can effectively make them strong language learners. We build competent diffusion language models at scale by first acquiring knowledge from massive data via masked language modeling pretraining thanks to their intrinsic connections. We then reprogram pretrained masked language models into diffusion language models via diffusive adaptation, wherein task-specific finetuning and instruction finetuning are explored to unlock their versatility in solving general language tasks. Experiments show that scaling diffusion language models consistently improves performance across downstream language tasks. We further discover that instruction finetuning can elicit zero-shot and few-shot in-context learning abilities that help tackle many unseen tasks by following natural language instructions, and show promise in advanced and challenging abilities such as reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2308_12219
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuning
Ye, Jiasheng
Zheng, Zaixiang
Bao, Yu
Qian, Lihua
Gu, Quanquan
Computation and Language
Artificial Intelligence
Machine Learning
The recent surge of generative AI has been fueled by the generative power of diffusion probabilistic models and the scalable capabilities of large language models. Despite their potential, it remains elusive whether diffusion language models can solve general language tasks comparable to their autoregressive counterparts. This paper demonstrates that scaling diffusion models w.r.t. data, sizes, and tasks can effectively make them strong language learners. We build competent diffusion language models at scale by first acquiring knowledge from massive data via masked language modeling pretraining thanks to their intrinsic connections. We then reprogram pretrained masked language models into diffusion language models via diffusive adaptation, wherein task-specific finetuning and instruction finetuning are explored to unlock their versatility in solving general language tasks. Experiments show that scaling diffusion language models consistently improves performance across downstream language tasks. We further discover that instruction finetuning can elicit zero-shot and few-shot in-context learning abilities that help tackle many unseen tasks by following natural language instructions, and show promise in advanced and challenging abilities such as reasoning.
title Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuning
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2308.12219