Large language models (LLMs) have shown great potential in complex reasoning tasks, yet their performance is often hampered by the scarcity of high-quality and reasoning-focused training datasets. Addressing this challenge, we propose Key-Point-Driven Data Synthesis (KPDDS), a novel data synthesis framework that synthesizes question-answer pairs by leveraging key points and exemplar practices from authentic data sources. KPDDS ensures the generation of novel questions with rigorous quality control and substantial scalability. As a result, we present KPMath, an extensive synthetic dataset tailored for mathematical reasoning, comprising over 800K question-answer pairs. Utilizing KPMath and augmenting it with additional reasoning-intensive corpora, we create the comprehensive KPMath-Plus dataset. The Qwen1.5-72B model, fine-tuned on KPMath-Plus, achieves 87.0% PASS@1 accuracy on GSM8K and 58.3% on MATH, surpassing competitors in the 7B to 70B range and best commercial models like GPT-4 across multiple math reasoning datasets.
MathAgent: Adversarial Evolution of Constraint Graphs for Mathematical Reasoning Data Synthesis
Huawei Large Model Data Technology Lab(华为大模型数据技术实验室);Tsinghua University(清华大学);Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));Kyoto University(京都大学)
JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
School of Information, Renmin University of China(中国人民大学信息学院);Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院);iFLYTEK Research(讯飞研究院);iFLYTEK AI Research (Central China)(讯飞人工智能研究(华中))
CoTEvol: Self-Evolving Chain-of-Thoughts for Data Synthesis in Mathematical Reasoning
Fudan University(复旦大学);Shanghai Innovation Institute(上海创新研究院);The Chinese University of Hong Kong(香港中文大学);Monash University(墨尔本大学);Independent Researcher(独立研究者);Shanghai Academy of AI for Science(上海人工智能科学研究院)
RV-Syn: Rational and Verifiable Mathematical Reasoning Data Synthesis based on Structured Function Library
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学人工智能学院);Ant Group(蚂蚁集团);Beijing Key Laboratory of Research on Large Models and Intelligent Governance(北京大型模型与智能治理重点实验室)
Mining or Synthesis? Rethinking Exploration Efficiency in Iterative Alignment of Mathematical Reasoning
Institute of Computing and Intelligence, Harbin Institute of Technology, Shenzhen, China(哈尔滨工业大学深圳研究院);Huawei Large Model Data Technology Lab(华为大模型数据技术实验室);Huawei Multimodal Model Lab(华为多模态模型实验室);Department of Statistics and Data Science, Tsinghua University, Beijing, China(清华大学统计与数据科学系)