ATHENA：基于思维扩展的数学推理
ATHENA: Mathematical Reasoning with Thought Expansion
AI总结：
针对现有数学推理模型思维过程受限、难适配现实多样表述的问题，提出模拟人类思维扩展的ATHENA架构，通过循环生成候选并筛选有效路径解题，在训练信息受限下仍取得新的最优效果。
摘要：
求解数学应用题取决于对问题的表述方式，这是模型理解人类语言表达的视角。现实场景中由于同一数学运算的表述方式多样，对此类方法的依赖度更高。已有研究通过有限的预测策略约束可用思维过程，未考虑其在获取数学知识中的重要性。我们提出基于注意力的思维扩展网络架构（Attention-based THought Expansion Network Architecture，ATHENA），以神经网络传播的形式模拟人类思维扩展机制，应对现实场景的挑战。思维扩展会循环生成承载上一步推导的可能数学表达式的候选思维，并通过选择通往目标的有效路径得出合理思路。实验表明，即便训练样本的信息量受限，ATHENA在应对多样化问题方面仍向理想模型迈进了一步，取得了新的SOTA（state-of-the-art，当前最优）水平。
英文摘要：
Solving math word problems depends on how to articulate the problems, the lens through which models view human linguistic expressions. Real-world settings count on such a method even more due to the diverse practices of the same mathematical operations. Earlier works constrain available thinking processes by limited prediction strategies without considering their significance in acquiring mathematical knowledge. We introduce Attention-based THought Expansion Network Architecture (ATHENA) to tackle the challenges of real-world practices by mimicking human thought expansion mechanisms in the form of neural network propagation. A thought expansion recurrently generates the candidates carrying the thoughts of possible math expressions driven from the previous step and yields reasonable thoughts by selecting the valid pathways to the goal. Our experiments show that ATHENA achieves a new state-of-the-art stage toward the ideal model that is compelling in variant questions even when the informativeness in training examples is restricted.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
