pith. sign in

arxiv: 2304.09102 · v1 · pith:GTBHEMK3new · submitted 2023-04-16 · 💻 cs.CL · cs.AI

Solving Math Word Problems by Combining Language Models With Symbolic Solvers

classification 💻 cs.CL cs.AI
keywords problemswordmathexternallanguagesolvingalgebraapproach
0
0 comments X
read the original abstract

Automatically generating high-quality step-by-step solutions to math word problems has many applications in education. Recently, combining large language models (LLMs) with external tools to perform complex reasoning and calculation has emerged as a promising direction for solving math word problems, but prior approaches such as Program-Aided Language model (PAL) are biased towards simple procedural problems and less effective for problems that require declarative reasoning. We propose an approach that combines an LLM that can incrementally formalize word problems as a set of variables and equations with an external symbolic solver that can solve the equations. Our approach achieves comparable accuracy to the original PAL on the GSM8K benchmark of math word problems and outperforms PAL by an absolute 20% on ALGEBRA, a new dataset of more challenging word problems extracted from Algebra textbooks. Our work highlights the benefits of using declarative and incremental representations when interfacing with an external tool for solving complex math word problems. Our data and prompts are publicly available at https://github.com/joyheyueya/declarative-math-word-problem.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Open Datasets in Learning Analytics: Trends, Challenges, and Best PRACTICE

    cs.CY 2026-02 accept novelty 8.0

    A survey of 172 open educational datasets from 204 papers across LAK, EDM, and AIED conferences reveals trends, 143 previously uncatalogued datasets, field gaps, and an 8-item PRACTICE checklist for better data publication.

  2. Factored Causal Representation Learning for Robust Reward Modeling in RLHF

    cs.LG 2026-01 unverdicted novelty 6.0

    A factored causal representation learning method improves robustness of reward models in RLHF by isolating causal factors from biases like length and sycophancy using adversarial gradient reversal.