Thinking Out of Order: When Output Order Stops Reflecting Reasoning Order in Diffusion Language Models

• URL: http://arxiv.org/abs/2601.22035v1
• Date: Thu, 29 Jan 2026 17:40:58 GMT
• Title: Thinking Out of Order: When Output Order Stops Reflecting Reasoning Order in Diffusion Language Models
• Abstract summary: Masked diffusion language models (MDLMs) iteratively refine all tokens in parallel to decouple order from output structure.<n>We present evidence that MDLMs achieve order robustness by stabilizing simpler tokens earlier in the diffusion process than complex ones.
• Score: 26.550350205533217
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autoregressive (AR) language models enforce a fixed left-to-right generation order, creating a fundamental limitation when the required output structure conflicts with natural reasoning (e.g., producing answers before explanations due to presentation or schema constraints). In such cases, AR models must commit to answers before generating intermediate reasoning, and this rigid constraint forces premature commitment. Masked diffusion language models (MDLMs), which iteratively refine all tokens in parallel, offer a way to decouple computation order from output structure. We validate this capability on GSM8K, Math500, and ReasonOrderQA, a benchmark we introduce with controlled difficulty and order-level evaluation. When prompts request answers before reasoning, AR models exhibit large accuracy gaps compared to standard chain-of-thought ordering (up to 67% relative drop), while MDLMs remain stable ($\leq$14% relative drop), a property we term "order robustness". Using ReasonOrderQA, we present evidence that MDLMs achieve order robustness by stabilizing simpler tokens (e.g., reasoning steps) earlier in the diffusion process than complex ones (e.g., final answers), enabling reasoning tokens to stabilize before answer commitment. Finally, we identify failure conditions where this advantage weakens, outlining the limits required for order robustness.

Related papers

• WhisperRec: Latent Reasoning for Efficient Foundation Recommendation Models [51.88075626243057]
  We propose WhisperRec, an efficient latent reasoning framework for foundation recommendation models (FRMs)<n>WhisperRec compresses teacher-generated Chain-of-Thought (CoT) into learnable latent reasoning tokens.<n>We show that WhisperRec consistently outperforms explicit-CoT methods and conventional baselines.
  arXiv  Detail & Related papers  (2026-07-29T08:48:35Z)
• DPRM: A Plug-in Doob h transform-induced Token-Ordering Module for Diffusion Language Models [76.12556589212666]
  We introduce DPRM (Doob h-transform Process Reward Model), a plug-in token-ordering module for diffusion language models.<n>DPRM starts from confidence-driven progressive ordering and gradually shifts to Doob h transform Process Reward guided ordering through online estimates.<n>Under tractable optimization assumptions, DPRM also yields a sample-complexity advantage over random and confidence-only ordering.
  arXiv  Detail & Related papers  (2026-04-27T11:50:26Z)
• CORE: Context-Robust Remasking for Diffusion Language Models [51.59514489363897]
  We propose Context-Robust Remasking (CORE), a training-free framework for inference-time revision.<n>Rather than trusting static token probabilities, CORE identifies context-brittle tokens by probing their sensitivity to targeted masked-context perturbations.<n>On LLaDA-8B-Base, CORE delivers consistent improvements across reasoning and code benchmarks, outperforming compute-matched baselines and improving MBPP by up to 9.2 percentage points.
  arXiv  Detail & Related papers  (2026-02-04T00:12:30Z)
• Parallelism and Generation Order in Masked Diffusion Language Models: Limits Today, Potential Tomorrow [30.201913054064363]
  Masked Diffusion Language Models promise parallel token generation and arbitrary-order decoding.<n>We characterize MDLM behavior along two dimensions -- parallelism strength and generation order.<n>We evaluate eight mainstream MDLMs on 58 benchmarks spanning knowledge, reasoning, and programming.
  arXiv  Detail & Related papers  (2026-01-22T02:39:36Z)
• The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models [67.58848748317506]
  Diffusion Large Language Models (dLLMs) break the rigid left-to-right constraint of traditional LLMs.<n>In this paper, we reveal a counter-intuitive reality: arbitrary order generation, in its current form, narrows rather than expands the reasoning boundary of dLLMs.
  arXiv  Detail & Related papers  (2026-01-21T16:41:58Z)
• Structured Reasoning for Large Language Models [59.215789462977206]
  We propose Structured Reasoning (SCR), a framework that decouples reasoning trajectories into explicit, evaluable, and trainable components.<n>SCR substantially improves reasoning efficiency and self-verification.<n>Compared with existing reasoning paradigms, it reduces output token length by up to 50%.
  arXiv  Detail & Related papers  (2026-01-12T04:04:01Z)
• You Only Forward Once: An Efficient Compositional Judging Paradigm [17.06658600909927]
  YOFO is a template-conditioned method that judges all requirements in a single forward pass.<n>It achieves state-of-the-art results on standard recommendation datasets.
  arXiv  Detail & Related papers  (2025-11-20T17:55:21Z)
• 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)
• Order Doesn't Matter, But Reasoning Does: Training LLMs with Order-Centric Augmentation [57.570754504160305]
  We introduce an order-centric data augmentation framework based on commutativity in logical reasoning.<n>By leveraging order-centric augmentations, models can develop a more flexible and generalized reasoning process.
  arXiv  Detail & Related papers  (2025-02-27T09:25:50Z)
• COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement [80.18490952057125]
  Iterative refinement has emerged as an effective paradigm for enhancing the capabilities of large language models (LLMs) on complex tasks. We propose Context-Wise Order-Agnostic Language Modeling (COrAL) to overcome these challenges. Our approach models multiple token dependencies within manageable context windows, enabling the model to perform iterative refinement internally.
  arXiv  Detail & Related papers  (2024-10-12T23:56:19Z)
• Premise Order Matters in Reasoning with Large Language Models [57.18850969634412]
  We show that large language models (LLMs) are surprisingly brittle to the ordering of the premises. We observe that LLMs achieve the best performance when the premise order aligns with the context required in intermediate reasoning steps.
  arXiv  Detail & Related papers  (2024-02-14T04:50:18Z)

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.