Solving Math Word Problems via Cooperative Reasoning induced Language Models
Preprint
Abstract
Large-scale pre-trained language models (PLMs) bring new opportunities to challenging problems, especially those that need high-level intelligence, such as the math word problem (MWPs). However, directly applying existing PLMs to MWPs can fail as the generation process lacks sufficient supervision and thus lacks fast adaptivity as humans. We notice that human reasoning has a dual reasoning framework that consists of an immediate reaction system (system 1) and a delicate reasoning system (system 2), where the entire reasoning is determined by their interaction. This inspires us to develop a cooperative reasoning-induced PLM for solving MWPs, called Cooperative Reasoning (CoRe), resulting in a human-like reasoning architecture with system 1 as the generator and system 2 as the verifier. In our approach, the generator is responsible for generating reasoning paths, and the verifiers are used to supervise the evaluation in order to obtain reliable feedback for the generator. We evaluate our CoRe framework on several mathematical reasoning datasets and achieve decent improvement over state-of-the-art methods, up to 9.6% increase over best baselines. Our codes are available at https://github.com/TianHongZXY/CoReKeywords
All Related Versions
This publication has 9 references indexed in Scilit:
- MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem SolversProceedings of the AAAI Conference on Artificial Intelligence, 2022
- Improving AlphaZero Using Monte-Carlo Graph SearchProceedings of the International Conference on Automated Planning and Scheduling, 2021
- Gender and Representation Bias in GPT-3 Generated Stories2021
- A Diverse Corpus for Evaluating and Developing English Math Word Problem Solvers2020
- Unit Dependency Graph and Its Application to Arithmetic Word Problem SolvingProceedings of the AAAI Conference on Artificial Intelligence, 2017
- Parsing Algebraic Word Problems into EquationsTransactions of the Association for Computational Linguistics, 2015
- Reasoning about Quantities in Natural LanguageTransactions of the Association for Computational Linguistics, 2015
- Solving General Arithmetic Word Problems2015
- In two minds: dual-process accounts of reasoningTrends in Cognitive Sciences, 2003