Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.15401 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908745309618176 |
|---|---|
| author | Ma, Xuetao Jiang, Wenbin Huang, Hua |
| author_facet | Ma, Xuetao Jiang, Wenbin Huang, Hua |
| contents | In-context learning (ICL) can significantly enhance the complex reasoning capabilities of large language models (LLMs), with the key lying in the selection and ordering of demonstration examples. Previous methods typically relied on simple features to measure the relevance between examples. We argue that these features are not sufficient to reflect the intrinsic connections between examples. In this study, we propose a curriculum ICL strategy guided by problem-solving logic. We select demonstration examples by analyzing the problem-solving logic and order them based on curriculum learning. Specifically, we constructed a problem-solving logic instruction set based on the BREAK dataset and fine-tuned a language model to analyze the problem-solving logic of examples. Subsequently, we selected appropriate demonstration examples based on problem-solving logic and assessed their difficulty according to the number of problem-solving steps. In accordance with the principles of curriculum learning, we ordered the examples from easy to hard to serve as contextual prompts. Experimental results on multiple benchmarks indicate that our method outperforms previous ICL approaches in terms of performance and efficiency, effectively enhancing the complex reasoning capabilities of LLMs. Our project will be released at https://github.com/maxuetao/CurriculumICL |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_15401 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Problem-Solving Logic Guided Curriculum In-Context Learning for LLMs Complex Reasoning Ma, Xuetao Jiang, Wenbin Huang, Hua Computation and Language Artificial Intelligence In-context learning (ICL) can significantly enhance the complex reasoning capabilities of large language models (LLMs), with the key lying in the selection and ordering of demonstration examples. Previous methods typically relied on simple features to measure the relevance between examples. We argue that these features are not sufficient to reflect the intrinsic connections between examples. In this study, we propose a curriculum ICL strategy guided by problem-solving logic. We select demonstration examples by analyzing the problem-solving logic and order them based on curriculum learning. Specifically, we constructed a problem-solving logic instruction set based on the BREAK dataset and fine-tuned a language model to analyze the problem-solving logic of examples. Subsequently, we selected appropriate demonstration examples based on problem-solving logic and assessed their difficulty according to the number of problem-solving steps. In accordance with the principles of curriculum learning, we ordered the examples from easy to hard to serve as contextual prompts. Experimental results on multiple benchmarks indicate that our method outperforms previous ICL approaches in terms of performance and efficiency, effectively enhancing the complex reasoning capabilities of LLMs. Our project will be released at https://github.com/maxuetao/CurriculumICL |
| title | Problem-Solving Logic Guided Curriculum In-Context Learning for LLMs Complex Reasoning |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2502.15401 |