Elementary Math Word Problem Generation using Large Language Models
Not on the map. Why?
Abstract (arXiv)
Mathematics is often perceived as a complex subject by students, leading to high failure rates in exams. To improve Mathematics skills, it is important to provide sample questions for students to practice problem-solving. Manually creating Math Word Problems (MWPs) is time consuming for tutors, because they have to type in natural language while adhering to grammar and spelling rules of the language. Early techniques that use pre-trained Language Models for MWP generation either require a tutor to provide the initial portion of the MWP, and/or additional information such as an equation. In this paper, we present an MWP generation system (MathWiz) based on Large Language Models (LLMs) that overcomes the need for additional input - the only input to our system is the number of MWPs needed, the grade and the type of question (e.g.~addition, subtraction). Unlike the existing LLM-based solutions for MWP generation, we carried out an extensive set of experiments involving different LLMs, prompting strategies, techniques to improve the diversity of MWPs, as well as techniques that employ human feedback to improve LLM performance. Human and automated evaluations confirmed that the generated MWPs are high in quality, with minimal spelling and grammar issues. However, LLMs still struggle to generate questions that adhere to the specified grade and question type requirements.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 47 of its 70 references that are in the map. First posted on arXiv 6 Jun 2025.
Builds on
47 of 70 references.
References · 47
- 2017Attention Is All You Needcited by 59,932
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
- 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
- 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
- 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
- 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
- 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
- 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
- 2023Mistral 7Bcited by 3,065
- 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
- 2022Training Compute-Optimal Large Language Modelscited by 2,927
- 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
35 more
- 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,813
- 2021BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-modelscited by 1,234
- 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,199
- 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 886
- 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 861
- 2021GPT Understands, Toocited by 715
- 2021P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Taskscited by 686
- 2019MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalismscited by 653
- 2024DeepSeek LLM: Scaling Open-Source Language Models with Longtermismcited by 621
- 2023WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instructcited by 618
- 2023A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPTcited by 612
- 2023The Falcon Series of Open Language Modelscited by 526
- 2018Texygen: A Benchmarking Platform for Text Generation Modelscited by 484
- 2024Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translationcited by 390
- 2023Understanding the Effects of RLHF on LLM Generalisation and Diversitycited by 386
- 2016Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Modelscited by 299
- 2023ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systemscited by 259
- 2022A Contrastive Framework for Neural Text Generationcited by 224
- 2020Participatory Research for Low-resourced Machine Translation: A Case Study in African Languagescited by 159
- 2023Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventionscited by 121
- 2024Limitations of the LLM-as-a-Judge Approach for Evaluating LLM Outputs in Expert Knowledge Taskscited by 102
- 2023LLM-Eval: Unified Multi-Dimensional Automatic Evaluation for Open-Domain Conversations with Large Language Modelscited by 100
- 2022On Decoding Strategies for Neural Text Generatorscited by 89
- 2023Exploring the Use of Large Language Models for Reference-Free Text Quality Evaluation: An Empirical Studycited by 85
- 2023A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4cited by 81
- 2022A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyondcited by 64
- 2021Math Word Problem Generation with Mathematical Consistency and Problem Context Constraintscited by 27
- 2023An Automated Survey of Generative Artificial Intelligence: Large Language Models, Architectures, Protocols, and Applicationscited by 20
- 2023Learning by Analogy: Diverse Questions Generation in Math Word Problemcited by 18
- 2024A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Techniquescited by 16
- 2022Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problemcited by 13
- 2023Fusion-Eval: Integrating Assistant Evaluators with LLMscited by 6
- 2024Adversarial Math Word Problem Generationcited by 6
- 2022Harnessing Knowledge and Reasoning for Human-Like Natural Language Generation: A Brief Reviewcited by 3
- 2024Large Language Models for Ingredient Substitution in Food Recipes using Supervised Fine-tuning and Direct Preference Optimizationcited by 1
Built on by
Not cited yet.