Yike Zhao
Research Subjects
Yike Zhao has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
Dahua Lin
The Chinese University of Hong Kong
2 shared publications- Fei Tan
Shanghai Institute of AI for Education East China Normal University 200062 Shanghai China
2 shared publications - Hanyue Du
School of Data Science and Engineering, East China Normal University, Shanghai, China
2 shared publications Shifan Han
Independent Researcher
2 shared publications- Simin Guo
University of Chicago
2 shared publications - Yunshi Lan
East China Normal University Shanghai China
2 shared publications
Latest Publications
- Open Access
More Data or Better Data? A Critical Analysis of Data Selection and Synthesis for Mathematical Reasoning
The reasoning capabilities of Large Language Models (LLMs) play a critical role in many downstream tasks, yet depend strongly on the quality of training data. Despite various proposed data construction methods, their practical utility in real-world pipelines remains underexplored. In this work, we conduct a comprehensive analysis of open-source datasets and data synthesis techniques for mathematical reasoning, evaluating them under a unified pipeline designed to mirror training and deployment scenarios. We further distill effective data selection strategies and identify practical methods suitable for industrial applications. Our findings highlight that structuring data in more interpretable formats, or distilling from stronger models often outweighs simply scaling up data volume. This study provides actionable guidance for integrating training data to enhance LLM capabilities, supporting both cost-effective data curation and scalable model enhancement. We hope this work will inspire further research on how to balance "more data" versus "better data" for real-world reasoning tasks.
Open AccessMore Data or Better Data? A Critical Analysis of Data Selection and Synthesis for Mathematical Reasoning
The reasoning capabilities of Large Language Models (LLMs) play a critical role in many downstream tasks, yet depend strongly on the quality of training data. Despite various proposed data construction methods, their practical utility in real-world pipelines remains underexplored. In this work, we conduct a comprehensive analysis of open-source datasets and data synthesis techniques for mathematical reasoning, evaluating them under a unified pipeline designed to mirror training and deployment scenarios. We further distill effective data selection strategies and identify practical methods suitable for industrial applications. Our findings highlight that structuring data in more interpretable formats, or distilling from stronger models often outweighs simply scaling up data volume. This study provides actionable guidance for integrating training data to enhance LLM capabilities, supporting both cost-effective data curation and scalable model enhancement. We hope this work will inspire further research on how to balance "more data" versus "better data" for real-world reasoning tasks.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 618-629
More Data or Better Data? A Critical Analysis of Data Selection and Synthesis for Mathematical Reasoning
Yike Zhao, Simin Guo, Ziqing Yang, Shifan Han, Dahua Lin, Fei Tan. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 618-629
Open AccessMore Data or Better Data? A Critical Analysis of Data Selection and Synthesis for Mathematical Reasoning
Yike Zhao, Simin Guo, Ziqing Yang, Shifan Han, Dahua Lin, Fei Tan. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track. 2025.
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 5321-5325
FlaCGEC: A Chinese Grammatical Error Correction Dataset with Fine-grained Linguistic Annotation
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 5321-5325
Open AccessFlaCGEC: A Chinese Grammatical Error Correction Dataset with Fine-grained Linguistic Annotation
- 8 October 2023
- Published by Springer Nature
- p. 325-336
Towards Robust Chinese Spelling Check Systems: Multi-round Error Correction with Ensemble Enhancement
- 8 October 2023
- Published by Springer Nature
- p. 325-336
Towards Robust Chinese Spelling Check Systems: Multi-round Error Correction with Ensemble Enhancement