{"total":19,"rows":[{"id":"2305.12524","title":"TheoremQA: A Theorem-driven Question Answering dataset","created":"2023-05-21","cited_by_count":192,"area":null},{"id":"2403.18105","title":"Large Language Models for Education: A Survey and Outlook","created":"2024-03-26","cited_by_count":188,"area":null},{"id":"2405.12209","title":"MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark","created":"2024-05-20","cited_by_count":105,"area":null},{"id":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91,"area":null},{"id":"2109.00799","title":"MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solvers","created":"2021-09-02","cited_by_count":39,"area":null},{"id":"2302.13814","title":"An Independent Evaluation of ChatGPT on Mathematical Word Problems (MWP)","created":"2023-02-23","cited_by_count":31,"area":null},{"id":"2312.07622","title":"Mathematical Language Models: A Survey","created":"2023-12-12","cited_by_count":24,"area":null},{"id":"2205.15683","title":"Why are NLP Models Fumbling at Elementary Math? A Survey of Deep Learning based Word Problem Solvers","created":"2022-05-31","cited_by_count":9,"area":null},{"id":"2205.08108","title":"Unbiased Math Word Problems Benchmark for Mitigating Solving Bias","created":"2022-05-17","cited_by_count":8,"area":null},{"id":"2407.05134","title":"Solving for X and Beyond: Can Large Language Models Solve Complex Math Problems with More-Than-Two Unknowns?","created":"2024-07-06","cited_by_count":7,"area":null},{"id":"2211.07455","title":"Towards Robust Numerical Question Answering: Diagnosing Numerical Capabilities of NLP Systems","created":"2022-11-14","cited_by_count":6,"area":null},{"id":"2308.11189","title":"Diversity Measures: Domain-Independent Proxies for Failure in Language Model Queries","created":"2023-08-22","cited_by_count":4,"area":null},{"id":"2209.10310","title":"Seeking Diverse Reasoning Logic: Controlled Equation Expression Generation for Solving Math Word Problems","created":"2022-09-21","cited_by_count":3,"area":null},{"id":"2305.18618","title":"Chatbots put to the test in math and logic problems: A preliminary comparison and assessment of ChatGPT-3.5, ChatGPT-4, and Google Bard","created":"2023-05-30","cited_by_count":3,"area":null},{"id":"2401.07518","title":"Survey of Natural Language Processing for Education: Taxonomy, Systematic Review, and Future Trends","created":"2024-01-15","cited_by_count":3,"area":null},{"id":"2510.17389","title":"EduAdapt: A Question Answer Benchmark Dataset for Evaluating Grade-Level Adaptability in LLMs","created":"2025-10-20","cited_by_count":3,"area":null},{"id":"2204.04686","title":"DISK: Domain-constrained Instance Sketch for Math Word Problem Generation","created":"2022-04-10","cited_by_count":1,"area":null},{"id":"2211.16022","title":"Textual Enhanced Contrastive Learning for Solving Math Word Problems","created":"2022-11-29","cited_by_count":1,"area":null},{"id":"2404.03938","title":"Data Augmentation with In-Context Learning and Comparative Evaluation in Math Word Problem Solving","created":"2024-04-05","cited_by_count":0,"area":null}],"next_cursor":null}