Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.04065 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909637006065664 |
|---|---|
| author | Wu, Muling Qian, Qi Liu, Wenhao Wang, Xiaohua Huang, Zisu Liang, Di Miao, LI Dou, Shihan Lv, Changze Wang, Zhenghua Xu, Zhibo Chen, Lina Li, Tianlong Zheng, Xiaoqing Huang, Xuanjing |
| author_facet | Wu, Muling Qian, Qi Liu, Wenhao Wang, Xiaohua Huang, Zisu Liang, Di Miao, LI Dou, Shihan Lv, Changze Wang, Zhenghua Xu, Zhibo Chen, Lina Li, Tianlong Zheng, Xiaoqing Huang, Xuanjing |
| contents | Large Language Models (LLMs) have achieved remarkable performance across various reasoning tasks, yet post-training is constrained by inefficient sample utilization and inflexible difficulty samples processing. To address these limitations, we propose Customized Curriculum Learning (CCL), a novel framework with two key innovations. First, we introduce model-adaptive difficulty definition that customizes curriculum datasets based on each model's individual capabilities rather than using predefined difficulty metrics. Second, we develop "Guided Prompting," which dynamically reduces sample difficulty through strategic hints, enabling effective utilization of challenging samples that would otherwise degrade performance. Comprehensive experiments on supervised fine-tuning and reinforcement learning demonstrate that CCL significantly outperforms uniform training approaches across five mathematical reasoning benchmarks, confirming its effectiveness across both paradigms in enhancing sample utilization and model performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_04065 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Progressive Mastery: Customized Curriculum Learning with Guided Prompting for Mathematical Reasoning Wu, Muling Qian, Qi Liu, Wenhao Wang, Xiaohua Huang, Zisu Liang, Di Miao, LI Dou, Shihan Lv, Changze Wang, Zhenghua Xu, Zhibo Chen, Lina Li, Tianlong Zheng, Xiaoqing Huang, Xuanjing Computation and Language Large Language Models (LLMs) have achieved remarkable performance across various reasoning tasks, yet post-training is constrained by inefficient sample utilization and inflexible difficulty samples processing. To address these limitations, we propose Customized Curriculum Learning (CCL), a novel framework with two key innovations. First, we introduce model-adaptive difficulty definition that customizes curriculum datasets based on each model's individual capabilities rather than using predefined difficulty metrics. Second, we develop "Guided Prompting," which dynamically reduces sample difficulty through strategic hints, enabling effective utilization of challenging samples that would otherwise degrade performance. Comprehensive experiments on supervised fine-tuning and reinforcement learning demonstrate that CCL significantly outperforms uniform training approaches across five mathematical reasoning benchmarks, confirming its effectiveness across both paradigms in enhancing sample utilization and model performance. |
| title | Progressive Mastery: Customized Curriculum Learning with Guided Prompting for Mathematical Reasoning |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2506.04065 |