EMNLP Findings2023
Three Questions Concerning the Use of Large Language Models to Facilitate Mathematics Learning
Abstract
Due to the remarkable language understanding and generation abilities of large language models (LLMs), their use in educational applications has been explored. However, little work has been done on investigating the pedagogical ability of LLMs in helping students to learn mathematics. In this position paper, we discuss the challenges associated with employing LLMs to enhance students' mathematical problem-solving skills by providing adaptive feedback. Apart from generating the wrong reasoning processes, LLMs can misinterpret the meaning of the question, and also exhibit difficulty in understanding the given questions' rationales when attempting to correct students' answers. Three research questions are formulated.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
4 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- PAL: Program-aided Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Ask-Before-Detection: Identifying and Mitigating Conformity Bias in LLM-Powered Error Detector for Math Word Problem Solutions cites Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model Tutors
- Toolformer: Language Models Can Teach Themselves to Use Tools cites PAL: Program-aided Language Models
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models cites Generate & Rank: A Multi-task Framework for Math Word Problems
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models cites Training language models to follow instructions with human feedback
- AgentCoMa: A Compositional Benchmark Mixing Commonsense and Mathematical Reasoning in Real-World Scenarios cites PAL: Program-aided Language Models
- AgentCoMa: A Compositional Benchmark Mixing Commonsense and Mathematical Reasoning in Real-World Scenarios cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Cited by top-tier papers4
- Relief or displacement? How teachers are negotiating generative AI's role in their professional practiceAayushi Dangol, Smriti Kotiyal, Robert Wolfe, Alex J. Bowers et al.CHI 2026 · 5 citations
- Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model TutorsNico Daheim, Jakub Macina, Manu Kapur, Iryna Gurevych et al.EMNLP 2024 · 1 citation
- AgentCoMa: A Compositional Benchmark Mixing Commonsense and Mathematical Reasoning in Real-World ScenariosLisa Alazraki, Lihu Chen, Ana Brassard, Joe Stacey et al.ACL 2026 · 1 citation
- Ask-Before-Detection: Identifying and Mitigating Conformity Bias in LLM-Powered Error Detector for Math Word Problem SolutionsHang Li, Tianlong Xu, Kaiqi Yang, Yucheng Chu et al.ACL 2025
Builds on7
- Training language models to follow instructions with human feedbackLong Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida et al.NeurIPS 2022 · 24,707 citations
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- Toolformer: Language Models Can Teach Themselves to Use ToolsTimo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu et al.NeurIPS 2023 · 5,989 citations
- PAL: Program-aided Language ModelsLuyu Gao, Aman Madaan, Shuyan Zhou, Uri Alon et al.ICML 2023 · 700 citations
- Generate & Rank: A Multi-task Framework for Math Word ProblemsJianhao Shen, Yichun Yin, Lin Li, Lifeng Shang et al.EMNLP Findings 2021 · 88 citations
Related papers
- Exposing the Achilles' Heel: Evaluating LLMs Ability to Handle Mistakes in Mathematical ReasoningJoykirat Singh, Akshay Uttama Nambi, Vibhav VineetACL 2025 · 10 citations
- Number Cookbook: Number Understanding of Language Models and How to Improve ItHaotong Yang, Yi Hu, Shijia Kang, Zhouchen Lin et al.ICLR 2025
- GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem SolversQintong Li, Leyang Cui, Xueliang Zhao, Lingpeng Kong et al.ACL 2024 · 9 citations
- No Need for Explanations: LLMs can implicitly learn from mistakes in-contextLisa Alazraki, Maximilian Mozes, Jon Ander Campos, Yi Chern Tan et al.EMNLP 2025
- Large Language Models Cannot Self-Correct Reasoning YetJie Huang, Xinyun Chen, Swaroop Mishra, Huaixiu Steven Zheng et al.ICLR 2024 · 858 citations
