mlsanityData to 14 Oct 2026

Let GPT be a Math Tutor: Teaching Math Word Problem Solvers with Customized Exercise Generation

arXiv 2305.14386 ↗First posted 22 May 2023cs.LG cs.AI cs.CLcited by 29

Not on the map. Why?

Abstract (arXiv)

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. Our approach is designed to consider the student model's weaknesses and foster a tailored learning experience by generating targeted exercises aligned with educational science principles, such as knowledge tracing and personalized learning. Concretely, we let GPT-3 be a math tutor and run two steps iteratively: 1) assessing the student model's current learning status on a GPT-generated exercise book, and 2) improving the student model by training it with tailored exercise samples generated by GPT-3. Experimental results reveal that our approach outperforms LLMs (e.g., GPT-3 and PaLM) in accuracy across three distinct benchmarks while employing significantly fewer parameters. Furthermore, we provide a comprehensive analysis of the various components within our methodology to substantiate their efficacy.

Key facts. Cited by 29 papers in the map (data through 14 Oct 2026). Builds on 38 of its 64 references that are in the map. First posted on arXiv 22 May 2023.

Builds on

38 of 64 references.

References · 38

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  7. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  8. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  9. 2022Emergent Abilities of Large Language Modelscited by 2,512
  10. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,407
  11. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,076
  12. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 878
26 more
  1. 2022Language Models are Multilingual Chain-of-Thought Reasonerscited by 530
  2. 2016Solving General Arithmetic Word Problemscited by 360
  3. 2022Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoningcited by 350
  4. 2022Large Language Models Are Reasoning Teacherscited by 329
  5. 2021A Diverse Corpus for Evaluating and Developing English Math Word Problem Solverscited by 318
  6. 2022Teaching Small Language Models to Reasoncited by 284
  7. 2021Symbolic Knowledge Distillation: from General Language Models to Commonsense Modelscited by 270
  8. 2022ZeroGen: Efficient Zero-shot Learning via Dataset Generationcited by 211
  9. 2022WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creationcited by 202
  10. 2023Active Prompting with Chain-of-Thought for Large Language Modelscited by 154
  11. 2022Explanations from Large Language Models Make Small Reasoners Bettercited by 124
  12. 2021Generate & Rank: A Multi-task Framework for Math Word Problemscited by 82
  13. 2022Knowledge Tracing: A Surveycited by 77
  14. 2022ProGen: Progressive Zero-shot Dataset Generation via In-context Feedbackcited by 67
  15. 2023Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Modelscited by 61
  16. 2018Translating a Math Word Problem to an Expression Treecited by 57
  17. 2022PromDA: Prompt-based Data Augmentation for Low-Resource NLU Taskscited by 51
  18. 2022Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extractioncited by 44
  19. 2022Automatic Generation of Socratic Subquestions for Teaching Math Word Problemscited by 43
  20. 2021MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solverscited by 39
  21. 2021MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solvingcited by 32
  22. 2021Seeking Patterns, Not just Memorizing Procedures: Contrastive Learning for Solving Math Word Problemscited by 30
  23. 2020Reverse Operation based Data Augmentation for Solving Math Word Problemscited by 15
  24. 2021Recall and Learn: A Memory-augmented Solver for Math Word Problemscited by 13
  25. 2022Unbiased Math Word Problems Benchmark for Mitigating Solving Biascited by 8
  26. 2022Analogical Math Word Problems Solving with Enhanced Problem-Solution Associationcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 13; 2025: 8; 2026: 3.

29 papers.

Sort:

By area:

  1. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 769
  2. 2024Large Language Models for Mathematical Reasoning: Progresses and Challengescited by 284
  3. 2023Learning From Mistakes Makes LLM Better Reasonercited by 101
  4. 2024LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancementcited by 70
  5. 2024A Survey on Deep Learning for Theorem Provingcited by 57
  6. 2025A Survey on Large Language Models for Mathematical Reasoningcited by 52
  7. 2024SceMQA: A Scientific College Entrance Level Multimodal Question Answering Benchmarkcited by 35
  8. 2023Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Modelscited by 21
  9. 2024Enhancing Critical Thinking in Education by means of a Socratic Chatbotcited by 21
  10. 2023MinT: Boosting Generalization in Mathematical Reasoning via Multi-View Fine-Tuningcited by 16
  11. 2025Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral Simulationcited by 15
  12. 2024Foundation Models for Education: Promises and Prospectscited by 10
17 more
  1. 2024Plan-Grounded Large Language Models for Dual Goal Conversational Settingscited by 8
  2. 2023Math Word Problem Solving by Generating Linguistic Variants of Problem Statementscited by 7
  3. 2025A Cooperative Multi-Agent Framework for Zero-Shot Named Entity Recognitioncited by 6
  4. 2023Knowledge Distillation of LLM for Automatic Scoring of Science Education Assessmentscited by 4
  5. 2024Multi-Intent Attribute-Aware Text Matching in Searchingcited by 4
  6. 2024DivTOD: Unleashing the Power of LLMs for Diversifying Task-Oriented Dialogue Representationscited by 4
  7. 2025Solving the Unsolvable: Translating Case Law in Hong Kongcited by 3
  8. 2025Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AIcited by 3
  9. 2024Vernacular? I Barely Know Her: Challenges with Style Control and Stereotypingcited by 2
  10. 2024Error-driven Data-efficient Large Multimodal Model Tuningcited by 2
  11. 2025Rehearse With User: Personalized Opinion Summarization via Role-Playing based on Large Language Modelscited by 2
  12. 2025Fine-Tuning and Prompt Engineering of LLMs, for the Creation of Multi-Agent AI for Addressing Sustainable Protein Production Challengescited by 2
  13. 2025Foundation of Intelligence: Review of Math Word Problems from Human Cognition Perspectivecited by 1
  14. 2024Data Augmentation with In-Context Learning and Comparative Evaluation in Math Word Problem Solvingcited by 0
  15. 2026SciText2Eq: Assessing LLMs for Explainable Equation Generation for Scientific Creativitycited by 0
  16. 2026AutoDP-LLM: Automating Data Pre-processing for Intrusion Detection Systems using Large Language Modelscited by 0
  17. 2026TutorLoop: Regulating Student Learning Behaviors via Sensor-in-the-Loop Generative Feedbackcited by 0