The authors ask whether failures on globally constrained problems come partly from the inference interface of next-token prediction.
Diffusion models beat autoregressive LLMs on globally constrained problems
Blackboard, a canvas-based inference method using mean confidence, pushes LLaDA-8B beyond same-scale and frontier autoregressive models on three structured reasoning benchmarks.
Top University
Woosang Jeon · Jaeyeon Kim · Sham Kakade · Yilun Du · Amrit Singh Bedi · Arun Kumar Chithanar · +3 more
Seoul National University · Harvard University · University of Central Florida
Research Digest··2 min read
The authors show that masked diffusion language models can outperform autoregressive LLMs on tasks requiring global constraints.
Why this paper
From Seoul National University and 2 others
In one line
Blackboard intelligence from diffusion language models surpasses autoregressive models on globally constrained problems by using mean confidence to guide search and revision.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors
- ✓Reports numbers on named benchmarks (3 benchmarks)
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§