扩散模型可打破生成顺序限制，让推理先于答案输出。
Thinking Out of Order: When Output Order Stops Reflecting Reasoning Order in Diffusion Language Models
- 用扩散机制并行优化所有词元，解耦计算顺序与输出结构
- 在答案前置任务中，准确率下降不超过14%，远优于传统模型
- 适合需要灵活输出顺序的复杂推理场景
自回归语言模型强制从左到右生成，当输出结构与自然推理冲突时（如要求先给答案再解释），会导致过早承诺答案。掩码扩散语言模型（MDLMs）通过迭代并行优化所有词元，可解耦计算顺序与输出结构。我们在GSM8K、Math500和新提出的ReasonOrderQA基准上验证该能力。当提示要求答案先于推理时，自回归模型准确率相对下降高达67%，而MDLMs仅下降≤14%，表现出“顺序鲁棒性”。通过ReasonOrderQA分析发现，MDLMs在扩散过程中更早稳定简单词元（如推理步骤），后稳定复杂词元（如最终答案），从而实现推理完成前不锁定答案。最后我们识别出该优势失效的边界条件，明确了顺序鲁棒性的适用范围。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。