Diffusion Language Models Know the Answer Before Decoding

• URL: http://arxiv.org/abs/2508.19982v3
• Date: Tue, 14 Oct 2025 03:42:04 GMT
• Title: Diffusion Language Models Know the Answer Before Decoding
• Authors: Pengxiang Li, Yefan Zhou, Dilxat Muhtar, Lu Yin, Shilin Yan, Li Shen, Yi Liang, Soroush Vosoughi, Shiwei Liu,
• Abstract summary: Diffusion language models (DLMs) have emerged as an alternative to autoregressive approaches.<n>Our work highlights and leverage an overlooked property of DLMs early answer convergence.<n>We introduce Prophet, a training-free fast decoding paradigm that enables early commit decoding.
• Score: 56.96815863705218
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion language models (DLMs) have recently emerged as an alternative to autoregressive approaches, offering parallel sequence generation and flexible token orders. However, their inference remains slower than that of autoregressive models, primarily due to the cost of bidirectional attention and the large number of refinement steps required for high quality outputs. In this work, we highlight and leverage an overlooked property of DLMs early answer convergence: in many cases, the correct answer can be internally identified by half steps before the final decoding step, both under semi-autoregressive and random remasking schedules. For example, on GSM8K and MMLU, up to 97% and 99% of instances, respectively, can be decoded correctly using only half of the refinement steps. Building on this observation, we introduce Prophet, a training-free fast decoding paradigm that enables early commit decoding. Specifically, Prophet dynamically decides whether to continue refinement or to go "all-in" (i.e., decode all remaining tokens in one step), using the confidence gap between the top-2 prediction candidates as the criterion. It integrates seamlessly into existing DLM implementations, incurs negligible overhead, and requires no additional training. Empirical evaluations of LLaDA-8B and Dream-7B across multiple tasks show that Prophet reduces the number of decoding steps by up to 3.4x while preserving high generation quality. These results recast DLM decoding as a problem of when to stop sampling, and demonstrate that early decode convergence provides a simple yet powerful mechanism for accelerating DLM inference, complementary to existing speedup techniques. Our code is publicly available at https://github.com/pixeli99/Prophet.

Related papers

• No Compute Left Behind: Rethinking Reasoning and Sampling with Masked Diffusion Models [42.158430350703505]
  Masked diffusion language models are trained to in-fill positions in randomly masked sequences.<n>We propose reasoning-as-infilling and multi-token entropy decoding.<n>Our work demonstrates that the training and compute used by MDLMs unlock many new inference and post-training methods.
  arXiv  Detail & Related papers  (2025-10-22T19:41:27Z)
• Saber: An Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model [98.35868970993232]
  Diffusion language models (DLMs) are emerging as a powerful and promising alternative to the dominant autoregressive paradigm.<n>We introduce efficient Sampling with Adaptive acceleration and Backtracking Enhanced Remasking (i.e., Saber) to achieve better inference speed and output quality in code generation.
  arXiv  Detail & Related papers  (2025-10-20T23:38:12Z)
• Direct Multi-Token Decoding [24.347862297812977]
  We introduce Direct Multi-Token Decoding (DMTD) as an inference paradigm for large language models (LLMs)<n>Unlike speculative decoding, our method introduces no additional parameters, auxiliary routines, or post-generation verification.<n>A fine-tuned DMTD Qwen3-4B model has already demonstrated promising results, achieving up to a 2x speedup with only minor performance loss.
  arXiv  Detail & Related papers  (2025-10-13T21:42:37Z)
• dParallel: Learnable Parallel Decoding for dLLMs [77.24184219948337]
  Diffusion large language models (dLLMs) offer parallel token prediction and lower inference latency.<n>Existing open-source models still require nearly token-length decoding steps to ensure performance.<n>We introduce dParallel, a simple and effective method that unlocks the inherent parallelism of dLLMs for fast sampling.
  arXiv  Detail & Related papers  (2025-09-30T16:32:52Z)
• Sequential Diffusion Language Models [110.06562906987052]
  Diffusion language models (DLMs) have strong theoretical efficiency but are limited by fixed-length decoding and incompatibility with key-value caches.<n>We introduce Next Sequence Prediction (NSP), which unifies next-token and next-block prediction.<n>We propose Sequential Diffusion Language Model (SDLM), which can retrofit pre-trained autoregressive language models (ALMs) at minimal cost.
  arXiv  Detail & Related papers  (2025-09-28T17:59:15Z)
• AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism [17.858104076062897]
  Large language models (LLMs) are increasingly used for long-content generation.<n>We propose AdaDecode, which accelerates decoding without requiring auxiliary models or changes to the original model parameters.<n>AdaDecode consistently achieves superior decoding throughput with up to 1.73x speedup.
  arXiv  Detail & Related papers  (2025-06-04T08:32:30Z)
• Accelerating Diffusion LLMs via Adaptive Parallel Decoding [50.9948753314669]
  We introduce adaptive parallel decoding (APD), a novel method that dynamically adjusts the number of tokens sampled in parallel.<n>APD provides markedly higher throughput with minimal quality degradations on downstream benchmarks.
  arXiv  Detail & Related papers  (2025-05-31T06:10:10Z)
• Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusion [16.99620863197586]
  Diffusion language models offer parallel token generation and inherent bidirectionality.<n>State-of-the-art diffusion models (e.g., Dream 7B, LLaDA 8B) suffer from slow inference.<n>We introduce Guided Diffusion, a training-free method that uses a lightweight pretrained autoregressive model to supervise token unmasking.<n>For the first time, diffusion language models achieve a comparable and even faster latency as the widely adopted autoregressive models.
  arXiv  Detail & Related papers  (2025-05-27T17:39:39Z)
• Dimple: Discrete Diffusion Multimodal Large Language Model with Parallel Decoding [53.82301522384719]
  We propose Dimple, the first Discrete Multimodal Large Language Model (DMLLM)<n>We design a novel training paradigm that combines an initial autoregressive phase with a subsequent diffusion phase.<n>Dimple-7B surpasses LLaVA- in performance by 3.9%, demonstrating that DMLLM can achieve performance comparable to that of autoregressive models.
  arXiv  Detail & Related papers  (2025-05-22T17:55:04Z)
• FIRP: Faster LLM inference via future intermediate representation prediction [54.897493351694195]
  FIRP generates multiple tokens instead of one at each decoding step. We conduct extensive experiments, showing a speedup ratio of 1.9x-3x in several models and datasets.
  arXiv  Detail & Related papers  (2024-10-27T15:53:49Z)
• Parallel Decoding via Hidden Transfer for Lossless Large Language Model Acceleration [54.897493351694195]
  We propose a novel parallel decoding approach, namely textithidden transfer, which decodes multiple successive tokens simultaneously in a single forward pass. In terms of acceleration metrics, we outperform all the single-model acceleration techniques, including Medusa and Self-Speculative decoding.
  arXiv  Detail & Related papers  (2024-04-18T09:17:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.