English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Automatically generating high-quality step-by-step solutions to math wordproblems has many applications in education. Recently, combining large languagemodels (LLMs) with external tools to perform complex reasoning and calculationhas emerged as a promising direction for solving math word problems, but priorapproaches such as Program-Aided Language model (PAL) are biased towards simpleprocedural problems and less effective for problems that require declarativereasoning. We propose an approach that combines an LLM that can incrementallyformalize word problems as a set of variables and equations with an externalsymbolic solver that can solve the equations. Our approach achieves comparableaccuracy to the original PAL on the GSM8K benchmark of math word problems andoutperforms PAL by an absolute 20% on ALGEBRA, a new dataset of morechallenging word problems extracted from Algebra textbooks. Our work highlightsthe benefits of using declarative and incremental representations wheninterfacing with an external tool for solving complex math word problems. Ourdata and prompts are publicly available athttps://github.com/joyheyueya/declarative-math-word-problem.

Solving Math Word Problems by Combining Language Models With Symbolic Solvers