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 …

While significant progress has been made in natural language processing (NLP), existing
methods exhibit limitations in effectively interpreting and processing diverse mathematical …

Reasoning in mathematical domains remains a significant challenge for relatively small
language models (LMs). Many current methods focus on specializing LMs in mathematical …

Current math word problem (MWP) solvers are usually Seq2Seq models trained by the (one-
problem; one-solution) pairs, each of which is made of a problem description and a solution …

Generating mathematical equations from natural language requires an accurate
understanding of the relations among math expressions. Existing approaches can be …

This paper presents a vector relation-centric algorithm for solving arithmetic word problems
(AWPs), which uses vector relation acquisition and scene knowledge to ensure the …

Large language models (LLMs) have demonstrated impressive capabilities in mathematical
problem solving, particularly in single turn question answering formats. However, real world …

Solving math word problems (MWP) is a challenging task for natural language processing
systems, as it requires to not only identify and comprehend the problem description within …

Math Solving requires both semantic understanding and relation reasoning. Most current
approaches treat it as a translation task from natural language to mathematical symbols …

Math word problem (MWP) represents a critical research area within reading
comprehension, where accurate comprehension of math problem text is crucial for …