Mathematical reasoning is a fundamental aspect of human intelligence and is applicable in
various fields, including science, engineering, finance, and everyday life. The development …

The problem of designing NLP solvers for math word problems (MWP) has seen sustained
research activity and steady gains in the test accuracy. Since existing solvers achieve high …

Mathematical reasoning, a core ability of human intelligence, presents unique challenges for
machines in abstract thinking and logical reasoning. Recent large pre-trained language …

Hybrid data combining both tabular and textual content (eg, financial reports) are quite
pervasive in the real world. However, Question Answering (QA) over such hybrid data is …

While the recent tree-based neural models have demonstrated promising results in
generating solution expression for the math word problem (MWP), most of these models do …

Most existing neural models for math word problems exploit Seq2Seq model to generate
solution expressions sequentially from left to right, whose results are far from satisfactory …

Geometry problem solving has attracted much attention in the NLP community recently. The
task is challenging as it requires abstract problem understanding and symbolic reasoning …

Sequence-to-sequence (SEQ2SEQ) models have been successfully applied to automatic
math word problem solving. Despite its simplicity, a drawback still remains: a math word …

The design of automatic solvers to arithmetic math word problems has attracted
considerable attention in recent years and a large number of datasets and methods have …

In this paper, we present a novel approach for distilling math word problem solving
capabilities from large language models (LLMs) into smaller, more efficient student models …