arXiv：cs.AI· Miao Li, Hanyang Jiang, Hengyu Fu, Baihe Huang, Yating Liu, Yuhang Cai, Changkun Guan, Zhongzhu Chen, Jiecheng Lu, Michael A. Boateng, Pascal Van Hentenryck·· 21 小时前
匹配合适的画布而非仅匹配答案：面向扩散语言模型的可预测性感知 SFT
Match the Canvas, Not Just the Answer: Predictability-Aware SFT for Diffusion Language Models
AI 导读
针对扩散语言模型（DLM）标准 SFT 中随机掩码带来的训练-推理不匹配问题，研究者提出 PACS 方法，用模型自身的可预测性来选择每个样本的注意力可见输入长度，并在参考 token 被置信度引导揭示前对其监督。在推理与代码生成基准上，PACS 平均准确率超过对比的 SFT 方法，单项基准较 vanilla SFT 最高提升 12.84 个百分点，代码将在论文发表后发布。
正文
Authors:Miao Li, Hanyang Jiang, Hengyu Fu, Baihe Huang, Yating Liu, Yuhang Cai, Changkun Guan, Zhongzhu Chen, Jiecheng Lu, Michael A. Boateng, Pascal Van Hentenryck
Abstract:Diffusion language models (DLMs) enable flexible parallel generation by resolving tokens according to the model's evolving predictability rather than a fixed left-to-right order. This flexibility, however, introduces training choices absent from standard autoregressive teacher forcing: which reference tokens are visible when a target is supervised and how much generation space is allocated. Standard supervised fine-tuning (SFT) typically makes these choices through random masking, independently of inference. Our analysis shows how this training-inference mismatch can misdirect supervision. Random masking can conceal prediction errors or penalize uncertainty that decoding would otherwise resolve, while the attention-visible input length can change which response formulations the model favors, even when the underlying solution is unchanged. Motivated by these findings, we propose Predictability-Aware Canvas Selection and Supervision (PACS), an SFT method. PACS uses the model's own predictability to select each example's attention-visible input length and supervises reference tokens immediately before their confidence-guided revelation. Across reasoning and code-generation benchmarks, PACS consistently achieves the highest mean accuracy among the compared SFT methods, with gains of up to 12.84 percentage points over vanilla SFT on individual benchmarks. Code will be released upon publication.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.18001 [cs.LG] |
| (or arXiv:2610.18001v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18001 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Miao Li [view email]
[v1]
Tue, 13 Oct 2026 09:02:51 UTC (534 KB)
来源：arXiv：cs.AI · arxiv.org