CaRE Compute-aware Remasking Evaluation Protocol for Masked Diffusion Language Models
CaRE introduces a standardized evaluation framework for comparing remasking strategies in masked diffusion language models (MDLMs). By standardizing the actual number of function evaluations (NFE), enforcing multi-metric reporting, and explicitly controlling stochasticity, CaRE reveals that temperature explains most MAUVE variance, compute-matched comparisons reverse several published strategy rankings, and informed remasking trades off with stochastic unmasking. High-entropy remasking reduces MAUVE by 0.296 at 256 steps at unmask_temp=0.25 (p=0.020). A leaderboard covering 12 open-weight MDLMs confirms these findings across architectures and scales.
-->
[Submitted on 4 Jun 2026]
Title:CaRE Compute-aware Remasking Evaluation Protocol for Masked Diffusion Language Models
View a PDF of the paper titled CaRE Compute-aware Remasking Evaluation Protocol for Masked Diffusion Language Models, by Yash Shah and 2 other authors
View PDF HTML (experimental)
Abstract:Masked diffusion language models (MDLMs) are advancing rapidly, yet the evaluation standards needed to reliably interpret their progress have not kept pace. Despite MDLMs becoming competitive with autoregressive language models, seven recent remasking papers evaluate under incompatible settings, varying nominal step counts, metrics, and sampling temperatures without jointly controlling these factors, rendering their strategy rankings largely incomparable and leaving open whether reported gains reflect algorithmic improvements or evaluation artifacts. We present CaRE, a compute-aware evaluation framework that audits MDLM remasking strategies by standardizing actual number of function evaluations (NFE), enforcing multi-metric reporting, and explicitly controlling stochasticity. Applied to 7 remasking strategies across LLaDA-8B-Base and Dream-7B-Base at 4 stochasticity levels and 3 step budgets on OpenWebText and LM1B, CaRE reveals that: (i) temperature explains the majority of MAUVE variance, (ii) compute-matched comparisons reverse several published strategy rankings, and (iii) informed remasking and stochastic unmasking are in tension, with high-entropy remasking reducing MAUVE by 0.296 at 256 steps at unmask_temp=0.25 (p=0.020). A CaRE leaderboard covering 12 open-weight MDLMs (150M to 8B parameters) shows that this interaction direction holds across architectures and scales. These findings demonstrate that current MDLM evaluations can systematically conflate algorithmic improvements with hidden choices of compute and stochasticity. We release the evaluation protocol, implementation, and leaderboard to ensure future remasking claims are reproducible and comparable.
Comments: updated version
Subjects:
Artificial Intelligence (cs.AI)
Cite as: arXiv:2607.24763 [cs.AI]
(or arXiv:2607.24763v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2607.24763
arXiv-issued DOI via DataCite
Submission history
From: Abhijit Chakraborty [view email] [v1] Thu, 4 Jun 2026 22:21:08 UTC (1,073 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled CaRE Compute-aware Remasking Evaluation Protocol for Masked Diffusion Language Models, by Yash Shah and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new | recent | 2026-07
Change to browse by:
cs
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?)