发表机构
Northeastern University; Hong Kong Polytechnic University; NiuTrans Research（东北大学; 香港理工大学; 纽创信研）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出Plan Canvas，通过固定推理区域和分离去噪时钟，在连续语言流中提升推理能力，在Deep ProsQA上准确率提升14个百分点。
AI 中文摘要
连续语言流通过同时去噪目标画布的所有位置来生成文本。为这种模型添加推理能力的自然方式是在答案之前写入一条轨迹，但轨迹长度会因问题而异。因此，在去噪过程中答案的起始位置是未知的，模型必须同时决定轨迹长度、每个轨迹标记的位置以及答案。我们提出Plan Canvas来固定轨迹与答案之间的边界。一个固定容量的规划区域容纳一条紧凑的轨迹，监督填充填补其未使用的位置，答案从固定位置开始。固定区域还允许为规划和答案分别设置去噪时钟。在保持自由轨迹基线中的轨迹文本、主干网络和画布长度不变的情况下，Plan Canvas在ProsQA和Deep ProsQA（一个具有更长证明的图基准）上提高了准确率。在Deep ProsQA上，准确率从73.0%提升到87.0%，使用有效路径回答的问题比例从30.8%提升到59.1%，并且在最长的证明上增益最大。
英文摘要
Continuous language flows generate text by denoising all positions of a target canvas together. The natural way to add reasoning to such a model is to write a trace ahead of the answer, but the trace length changes from question to question. The answer start is therefore unknown during denoising, and the model has to decide the trace length, the place of every trace token, and the answer at the same time. We propose Plan Canvas to fix the boundary between the trace and the answer. A plan region of fixed capacity holds a compact trace, supervised padding fills its unused positions, and the answer starts at a fixed position. The fixed regions also allow separate denoising clocks for the plan and for the answer. With the trace text, backbone, and canvas length of the free-trace baseline held fixed, Plan Canvas improves accuracy on ProsQA and on Deep ProsQA, a graph benchmark with longer proofs. On Deep ProsQA, accuracy rises from 73.0\% to 87.0\%, the share of questions answered with a valid path rises from 30.8\% to 59.1\%, and the gain is largest on the longest proofs.
