Papers › ATHENA: Mathematical Reasoning with Thought Expansion

ATHENA: Mathematical Reasoning with Thought Expansion

2 Nov 2023EMNLP 2023 12arXiv:2311.01036archive 2025-07-28

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.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

the-jb/athena-math officialmentioned in papermentioned on GitHubpytorch report

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

MathMath Word Problem SolvingMathematical Reasoning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
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