Language Modeling on Pubmed (test)
39.74PerplexityLDDM-M
Evaluation results
| Method | Links | |
|---|---|---|
| LDDM-MDiffusion Framework=Masked Diffusion, Training Steps=1 million, Training Dataset=OpenWebText2025.10 | 39.74 | |
| VADDZero-shot=true, Trained on=OpenWebText, Training iterations=1M2025.05 | 40.62 | |
| EDLM-NCEzero-shot=true2024.10 | 41.8 | |
| MLDMzero-shot=true2024.10 | 41.89 | |
| MDLMDiffusion Framework=Masked Diffusion, Training Steps=1 million, Training Dataset=OpenWebText, Retrained=true2025.10 | 41.94 | |
| MDLMZero-shot=true, Trained on=OpenWebText, Training iterations=1M, Reproduced=true2025.05 | 42.43 | |
| SEDDzero-shot=true2024.10 | 44.53 | |
| LDDM-UDiffusion Framework=Uniform Diffusion, Training Steps=1 million, Training Dataset=OpenWebText2025.10 | 45.05 | |
| SEDD AbsorbDiffusion Framework=Masked Diffusion, Training Steps=1 million, Training Dataset=OpenWebText, Retrained=true2025.10 | 45.25 | |
| EDLM-ARzero-shot=true2024.10 | 45.9 | |
| UDLMDiffusion Framework=Uniform Diffusion, Training Steps=1 million, Training Dataset=OpenWebText, Retrained=true2025.10 | 46.18 | |
| EDLM-coARzero-shot=true2024.10 | 46.31 | |
| ARzero-shot=true2024.10 | 49.01 | |
| GPT-2Zero-shot=true, Trained on=OpenWebText, Training iterations=1M2025.05 | 49.01 |