{"work":{"id":"e791a2f0-3b75-4c5b-84e1-d297d96e42f0","openalex_id":"https://openalex.org/W4386978002","doi":"10.48550/arxiv.2309.12284","arxiv_id":"2309.12284","raw_key":null,"title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","authors":null,"authors_text":"Longhui Yu, Weisen Jiang, Han Shi, Jincheng Yu, Zhengying Liu, Yu Zhang","year":2023,"venue":"cs.CL","abstract":"Large language models (LLMs) have pushed the limits of natural language understanding and exhibited excellent problem-solving ability. Despite the great success, most existing open-source LLMs (e.g., LLaMA-2) are still far away from satisfactory for solving mathematical problem due to the complex reasoning procedures. To bridge this gap, we propose MetaMath, a fine-tuned language model that specializes in mathematical reasoning. Specifically, we start by bootstrapping mathematical questions by rewriting the question from multiple perspectives without extra knowledge, which results in a new dataset called MetaMathQA. Then we fine-tune the LLaMA-2 models on MetaMathQA. Experimental results on two popular benchmarks (i.e., GSM8K and MATH) for mathematical reasoning demonstrate that MetaMath outperforms a suite of open-source LLMs by a significant margin. Our MetaMath-7B model achieves 66.4% on GSM8K and 19.4% on MATH, exceeding the state-of-the-art models of the same size by 11.5% and 8.7%. Particularly, MetaMath-70B achieves an accuracy of 82.3% on GSM8K, slightly better than GPT-3.5-Turbo. We release all the MetaMathQA dataset, the MetaMath models with different model sizes and the training code for public use.","external_url":"https://arxiv.org/abs/2309.12284","cited_by_count":28,"metadata_source":"pith","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":"2309.12284","created_at":"2026-05-09T03:26:25.594531+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","render_title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models"},"hub":{"state":{"work_id":"e791a2f0-3b75-4c5b-84e1-d297d96e42f0","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":65,"external_cited_by_count":28,"distinct_field_count":7,"first_pith_cited_at":"2023-09-11T17:47:22+00:00","last_pith_cited_at":"2026-07-02T07:02:44+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-22T10:49:29.186924+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"dataset","n":4},{"context_role":"background","n":3},{"context_role":"baseline","n":1}],"polarity_counts":[{"context_polarity":"use_dataset","n":4},{"context_polarity":"background","n":2},{"context_polarity":"baseline","n":1},{"context_polarity":"unclear","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}