A Survey of Inductive Reasoning for Large Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911587244179456 |
|---|---|
| author | Chen, Kedi Ruan, Dezhao Dan, Yuhao Wang, Yaoting Yan, Siyu Wu, Xuecheng Zhang, Yinqi Chen, Qin Zhou, Jie He, Liang Qi, Biqing Li, Linyang Guo, Qipeng Shi, Xiaoming Zhang, Wei |
| author_facet | Chen, Kedi Ruan, Dezhao Dan, Yuhao Wang, Yaoting Yan, Siyu Wu, Xuecheng Zhang, Yinqi Chen, Qin Zhou, Jie He, Liang Qi, Biqing Li, Linyang Guo, Qipeng Shi, Xiaoming Zhang, Wei |
| contents | Reasoning is an important task for large language models (LLMs). Among all the reasoning paradigms, inductive reasoning is one of the fundamental types, which is characterized by its particular-to-general thinking process and the non-uniqueness of its answers. The inductive mode is crucial for knowledge generalization and aligns better with human cognition, so it is a fundamental mode of learning, hence attracting increasing interest. Despite the importance of inductive reasoning, there is no systematic summary of it. Therefore, this paper presents the first comprehensive survey of inductive reasoning for LLMs. First, methods for improving inductive reasoning are categorized into three main areas: post-training, test-time scaling, and data augmentation. Then, current benchmarks of inductive reasoning are summarized, and a unified sandbox-based evaluation approach with the observation coverage metric is derived. Finally, we offer some analyses regarding the source of inductive ability and how simple model architectures and data help with inductive tasks, providing a solid foundation for future research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_10182 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Survey of Inductive Reasoning for Large Language Models Chen, Kedi Ruan, Dezhao Dan, Yuhao Wang, Yaoting Yan, Siyu Wu, Xuecheng Zhang, Yinqi Chen, Qin Zhou, Jie He, Liang Qi, Biqing Li, Linyang Guo, Qipeng Shi, Xiaoming Zhang, Wei Computation and Language Artificial Intelligence Reasoning is an important task for large language models (LLMs). Among all the reasoning paradigms, inductive reasoning is one of the fundamental types, which is characterized by its particular-to-general thinking process and the non-uniqueness of its answers. The inductive mode is crucial for knowledge generalization and aligns better with human cognition, so it is a fundamental mode of learning, hence attracting increasing interest. Despite the importance of inductive reasoning, there is no systematic summary of it. Therefore, this paper presents the first comprehensive survey of inductive reasoning for LLMs. First, methods for improving inductive reasoning are categorized into three main areas: post-training, test-time scaling, and data augmentation. Then, current benchmarks of inductive reasoning are summarized, and a unified sandbox-based evaluation approach with the observation coverage metric is derived. Finally, we offer some analyses regarding the source of inductive ability and how simple model architectures and data help with inductive tasks, providing a solid foundation for future research. |
| title | A Survey of Inductive Reasoning for Large Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2510.10182 |