ATHENA: Mathematical Reasoning with Thought Expansion
JB. Kim, Hazel Kim, Joonghyuk Hahn, Yo-Sub Han
Abstract
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. 1 Context The school playground was originally [80] meters long and [40] meters wide. Later when the school is remodeled, the length is increased by [10] meters and the width is increased by [15] meters. Train on an example of a question-solution pair under the context above. Question How many square meters is the original playground area? Solution (80 × 40) Test on variant questions that share the context above. Q0 How many times the length of the original playground was the width? DeductReasoner ATHENA UnbiasedMWP (80 + 10) × (40 + 15) -(80 × 40) (X) UnbiasedMWP (80 + 10) × (40 -15) (X) UnbiasedMWP (1:N) 80 ÷ 40 (O) UnbiasedMWP (1:N) 80 ÷ 40 (O) Q1 How many square meters is the current playground area? DeductReasoner ATHENA UnbiasedMWP (80 + 10) × (40 + 15) -(80 × 40) (X) UnbiasedMWP (80 + 10) × (40 + 15) (O) UnbiasedMWP (1:N) 80 × 40 (X) UnbiasedMWP (1:N) (80 + 10) × (40 + 15) (O) Q2 How many square meters are increased by the current playground area compared to the original one? DeductReasoner ATHENA UnbiasedMWP (80 + 10) × (40 + 15) -(80 × 40) (O) UnbiasedMWP (80 + 10) × (40 + 15) -(80 × 40) (O) UnbiasedMWP (1:N) 80 × 40 (X) UnbiasedMWP (1:N) (80 + 10) × (40 + 15) -(80 × 40) (O) An example with a lexically similar context to that of above from the UnbiasedMWP Context The school basketball court was [20] meters long and [12] meters wide. After the renovation, the length is increased by [8] meters, and the width increases by [3] meters. Question How many square meters are increased? Solution (20 + 8) × (12 + 3) -(20 × 12
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers1
Ask how each one uses itBuilds on8
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- On Layer Normalization in the Transformer ArchitectureRuibin Xiong, Yunchang Yang, Di He, Kai Zheng et al.ICML 2020 · 1,388 citations
- Graph-to-Tree Learning for Solving Math Word ProblemsJipeng Zhang, Lei Wang, Roy Ka-Wei Lee, Yi Bin et al.ACL 2020 · 129 citations
- HMS: A Hierarchical Solver with Dependency-Enhanced Understanding for Math Word ProblemXin Lin, Zhenya Huang, Hongke Zhao, Enhong Chen et al.AAAI 2021 · 70 citations
- Semantically-Aligned Universal Tree-Structured Solver for Math Word ProblemsJinghui Qin, Lihui Lin, Xiaodan Liang, Rumin Zhang et al.EMNLP 2020 · 62 citations
Related papers
- A Knowledge-Aware Sequence-to-Tree Network for Math Word Problem SolvingQinzhuo Wu, Qi Zhang, Jinlan Fu, Xuanjing HuangEMNLP 2020 · 71 citations
- Improving Math Word Problems with Pre-trained Knowledge and Hierarchical ReasoningWeijiang Yu, Yingpeng Wen, Fudan Zheng, Nong XiaoEMNLP 2021 · 30 citations
- Learning to Reason Deductively: Math Word Problem Solving as Complex Relation ExtractionZhanming Jie, Jierui Li, Wei LuACL 2022
- ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning ModelsChung-En Sun, Ge Yan, Tsui-Wei WengEMNLP 2025
- Scaling Linear Attention Capacity with Sparse State ExpansionYuqi Pan, Yongqi An, Zheng Li, Yuhong Chou et al.ICLR 2026 · 3 citations
