Skip to content
conftrace_
2026 EMNLP EMNLP 2026

CD4LM: Consistency Distillation and aDaptive Decoding for Diffusion Language Models

AbstractDiffusion language models (DLMs) accelerate generation by decoding multiple tokens in parallel, but pushing them to fast decoding often sacrifices accuracy. We attribute this to a static-to-dynamic mismatch: training optimizes local denoising under fixed schedules, while fast inference skips steps and encounters irregular mask patterns. Existing accelerators largely address only one side of this problem. Training-free inference methods speed up decoding without changing the model, leaving the mismatch unresolved; training-side distillation methods adapt the model, but often tie the student to a specific decoding trajectory, limiting composability and still suffering accuracy loss. We propose CD4LM, a composable framework for accurate DLM acceleration. Its core training component, Discrete-Space Consistency Distillation (DSCD) trains a trajectory-invariant student on diverse masked states, reducing the mismatch without fixing a decoding policy. We pair DSCD with a lightweight Confidence-Adaptive Decoder, while keeping the trained student compatible with external inference-side accelerators. On GSM8K, CD4LM preserves accuracy while achieving a 5.18× speedup; stacking CD4LM with per-step cache accelerators further pushes speedup to 9.73× at teacher-level accuracy, suggesting a scalable path for combining training-side robustness with future decoding advances.

More from EMNLP 2026

All EMNLP 2026 papers →