pith. sign in

arxiv: 2601.12247 · v3 · pith:T7RLCRCTnew · submitted 2026-01-18 · 💻 cs.CL · cs.AI· cs.LG

Plan, Verify and Fill: A Structured Parallel Decoding Approach for Diffusion Language Models

classification 💻 cs.CL cs.AIcs.LG
keywords decodingdiffusionevaluationsgloballanguagemodelsparadigmparallel
0
0 comments X
read the original abstract

Diffusion Language Models (DLMs) present a promising non-sequential paradigm for text generation, distinct from standard autoregressive (AR) approaches. However, current decoding strategies often adopt a reactive stance, underutilizing the global bidirectional context to dictate global trajectories. To address this, we propose Plan-Verify-Fill (PVF), a training-free paradigm that grounds planning via quantitative validation. PVF actively constructs a hierarchical skeleton by prioritizing high-leverage semantic anchors and employs a verification protocol to operationalize pragmatic structural stopping where further deliberation yields diminishing returns. Extensive evaluations on LLaDA-8B-Instruct and Dream-7B-Instruct demonstrate that PVF reduces the Number of Function Evaluations (NFE) by up to 65% compared to confidence-based parallel decoding across benchmark datasets, unlocking superior efficiency without compromising accuracy.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.