Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation
This paper introduces On-Policy Diffusion Language Model (OPDLM), which transforms autoregressive models into diffusion language models via on-policy distillation, addressing distribution shifts. OPDLM achieves strong performance with 15x to 7,000x fewer training tokens across various tasks, positioning DLM transformation as a form of ARLM post-training.
[2606.06712] Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation
[Submitted on 4 Jun 2026]
Title:Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation
View a PDF of the paper titled Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation, by Xingyu Su and 8 other authors
View PDF
Abstract:We study the transformation of autoregressive models (ARLMs) into diffusion language models (DLMs). Rather than pretraining from scratch, prior work replaces the causal attention in ARLMs with bidirectional attention and then trains the resulting model using a DLM objective. However, these approaches incur two distribution shifts. First, transitioning from a next-token prediction objective to a DLM objective can discard knowledge acquired by the ARLM during training. Second, standard DLMs suffer from a train-inference mismatch, as the training loss is defined on randomly masked sequences rather than the trajectories encountered at inference produced by confidence-based decoding. To address both challenges, we introduce an On-Policy Diffusion Language Model (OPDLM) in which On-Policy Distillation (OPD) is employed for ARLM-to-DLM transformation. Specifically, OPDLM is trained via self-OPD, where the student, an ARLM with bidirectional attention, generates its own trajectories, and the teacher, the original frozen ARLM, distills its knowledge by providing target logits on these trajectories. By training directly in an on-policy manner, OPDLM eliminates the train-inference mismatch in DLMs, while distillation from the original model enhances knowledge retention from the ARLM. Empirical results demonstrate that OPDLM requires 15x to 7,000x fewer training tokens with strong performance across a wide variety of tasks. OPDLM avoids the prohibitive cost of DLM pretraining and positions DLM transformation as a form of ARLM post-training.
Subjects:
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
Cite as: arXiv:2606.06712 [cs.CL]
(or arXiv:2606.06712v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2606.06712
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Xingyu Su [view email] [v1] Thu, 4 Jun 2026 20:58:08 UTC (1,688 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation, by Xingyu Su and 8 other authors
View PDF
TeX Source
view license
Current browse context:
cs.CL
new | recent | 2026-06
Change to browse by:
cs cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)