Papers › ATHENA: Mathematical Reasoning with Thought Expansion
ATHENA: Mathematical Reasoning with Thought Expansion
JB. Kim, Hazel Kim, Joonghyuk Hahn, Yo-Sub Han
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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Math Word Problem Solving | ASDiv-A | ATHENA (roberta-large) | Execution Accuracy | 91 | #1 of 9 | Archive leaderboard | report |
| Math Word Problem Solving | ASDiv-A | ATHENA (roberta-base) | Execution Accuracy | 86.4 | #3 of 9 | Archive leaderboard | report |
| Math Word Problem Solving | MAWPS | ATHENA (roberta-large) | Accuracy (%) | 93 | #3 of 25 | Archive leaderboard | report |
| Math Word Problem Solving | MAWPS | ATHENA (roberta-base) | Accuracy (%) | 92.2 | #6 of 25 | Archive leaderboard | report |
| Math Word Problem Solving | Math23K | ATHENA (roberta-large) | Accuracy (training-test) | 86.5 | #16 of 19 | Archive leaderboard | report |
| Math Word Problem Solving | Math23K | ATHENA (roberta-base) | Accuracy (training-test) | 84.4 | #17 of 19 | Archive leaderboard | report |
| Math Word Problem Solving | SVAMP | ATHENA (roberta-large) | Execution Accuracy | 54.8 | #17 of 26 | Archive leaderboard | report |
| Math Word Problem Solving | SVAMP | ATHENA (roberta-base) | Execution Accuracy | 45.6 | #20 of 26 | Archive leaderboard | report |
| Math Word Problem Solving | SVAMP (1:N) | ATHENA (roberta-large) | Execution Accuracy | 67.8 | #1 of 2 | Archive leaderboard | report |
| Math Word Problem Solving | SVAMP (1:N) | ATHENA (roberta-base) | Execution Accuracy | 52.5 | #2 of 2 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections