A text-infilling objective that masks equations in math solutions improves LLM mathematical reasoning over Masked Thought on GSM8K, MATH, and GSM-Symbolic.
Bender, Timnit Gebru, Angelina McMillan-Major, and Shmargaret Shmitchell
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ClozeMath: Improving Mathematical Reasoning in Language Models by Learning to Fill Equations
A text-infilling objective that masks equations in math solutions improves LLM mathematical reasoning over Masked Thought on GSM8K, MATH, and GSM-Symbolic.